https://agentprov.com 2026-10-27 https://agentprov.com/model 2026-10-27 https://agentprov.com/stats 2026-10-27 https://agentprov.com/incidents 2026-10-27 https://agentprov.com/methodology 2026-10-27 https://agentprov.com/program 2026-10-27 https://agentprov.com/incidents/2024-01-18-dpd-ai-chatbot-malfunction 2024-01-18 https://agentprov.com/incidents/2024-02-poisonedrag-research 2024-02-01 https://agentprov.com/incidents/2024-02-14-air-canada-chatbot-lawsuit-ruling 2024-02-14 https://agentprov.com/incidents/2024-03-chatgpt-plugin-extension-vulnerabilities 2024-03-01 https://agentprov.com/incidents/2024-03-openai-compromised-credentials-on-dark-web 2024-03-01 https://agentprov.com/incidents/2024-04-hugging-face-cross-tenant-attack 2024-04-01 https://agentprov.com/incidents/2024-04-02-many-shot-jailbreaking-research 2024-04-02 https://agentprov.com/incidents/2024-05-github-copilot-training-data-secret-leakage 2024-05-01 https://agentprov.com/incidents/2024-06-mcdonald-s-ends-ai-drive-thru-after-failures 2024-06-01 https://agentprov.com/incidents/2024-06-hugging-face-spaces-breach 2024-06-01 https://agentprov.com/incidents/2024-06-25-rabbit-r1-hardcoded-api-keys 2024-06-25 https://agentprov.com/incidents/2024-07-grok-ai-election-misinformation 2024-07-01 https://agentprov.com/incidents/2024-07-chatgpt-macos-cleartext-storage 2024-07-01 https://agentprov.com/incidents/2024-07-microsoft-365-copilot-ascii-smuggling 2024-07-01 https://agentprov.com/incidents/2024-08-06-microsoft-copilot-studio-ssrf 2024-08-06 https://agentprov.com/incidents/2024-08-08-lolcopilot-black-hat-usa-2024-copilot-attacks 2024-08-08 https://agentprov.com/incidents/2024-08-20-slack-ai-prompt-injection-and-data-exfiltration 2024-08-20 https://agentprov.com/incidents/2024-09-chatgpt-spaiware-persistent-memory-exploitation 2024-09-01 https://agentprov.com/incidents/2024-09-25-nvidia-container-toolkit-vulnerability 2024-09-25 https://agentprov.com/incidents/2024-10-17-imprompter-attack-on-ai-chatbots 2024-10-17 https://agentprov.com/incidents/2024-10-22-claude-computer-use-launch-security-warnings 2024-10-22 https://agentprov.com/incidents/2024-11-microsoft-copilot-exposes-private-github-repos 2024-11-01 https://agentprov.com/incidents/2024-11-microsoft-copilot-studio-xss 2024-11-01 https://agentprov.com/incidents/2024-11-22-freysa-ai-agent-game-function-manipulation 2024-11-22 https://agentprov.com/incidents/2024-12-chatgpt-search-manipulation-via-hidden-text 2024-12-01 https://agentprov.com/incidents/2024-12-04-ultralytics-pypi-supply-chain-attack 2024-12-04 https://agentprov.com/incidents/2025-01-24-omnigpt-data-breach 2025-01-24 https://agentprov.com/incidents/2025-02-google-gemini-prompt-injection-via-calendar-invites 2025-02-01 https://agentprov.com/incidents/2025-02-21-bybit-1-5b-cryptocurrency-heist 2025-02-21 https://agentprov.com/incidents/2025-03-15-tj-actions-changed-files-github-actions-supply-chain-attack 2025-03-15 https://agentprov.com/incidents/2025-03-18-rules-file-backdoor-attack-on-cursor-and-copilot 2025-03-18 https://agentprov.com/incidents/2025-04-mcp-tool-poisoning-whatsapp-data-exfiltration 2025-04-01 https://agentprov.com/incidents/2025-05-elizaos-memory-injection-vulnerability 2025-05-01 https://agentprov.com/incidents/2025-05-langflow-cisa-kev-addition-confirmed-active-exploitation 2025-05-01 https://agentprov.com/incidents/2025-06-langflow-flodrix-botnet-exploitation 2025-06-01 https://agentprov.com/incidents/2025-06-echoleak-microsoft-365-copilot-zero-click-prompt-injection 2025-06-01 https://agentprov.com/incidents/2025-06-github-copilot-camoleak 2025-06-01 https://agentprov.com/incidents/2025-06-anthropic-filesystem-mcp-server-escaperoute 2025-06-01 https://agentprov.com/incidents/2025-07-mcp-remote-critical-rce 2025-07-01 https://agentprov.com/incidents/2025-07-09-hugging-face-poisoned-gguf-templates 2025-07-09 https://agentprov.com/incidents/2025-07-17-amazon-q-vs-code-extension-compromise 2025-07-17 https://agentprov.com/incidents/2025-08-claude-code-inverseprompt-command-injection 2025-08-01 https://agentprov.com/incidents/2025-08-claude-code-websocket-auth-bypass 2025-08-01 https://agentprov.com/incidents/2025-08-openai-codex-cli-command-injection 2025-08-01 https://agentprov.com/incidents/2025-08-github-copilot-rce-via-prompt-injection 2025-08-01 https://agentprov.com/incidents/2025-08-cursor-curxecute-rce-via-slack-mcp 2025-08-01 https://agentprov.com/incidents/2025-08-cursor-mcpoison-silent-backdoor 2025-08-01 https://agentprov.com/incidents/2025-08-varonis-reprompt-microsoft-copilot-single-click-data-theft 2025-08-01 https://agentprov.com/incidents/2025-08-20-salesloft-drift-oauth-supply-chain-breach 2025-08-20 https://agentprov.com/incidents/2025-09-salesforce-agentforce-forcedleak 2025-09-01 https://agentprov.com/incidents/2025-10-claude-code-rce-via-hooks 2025-10-01 https://agentprov.com/incidents/2025-10-langflow-account-takeover-and-rce-chain 2025-10-01 https://agentprov.com/incidents/2025-11-servicenow-now-assist-second-order-prompt-injection 2025-11-01 https://agentprov.com/incidents/2025-11-crewai-uncrew-github-token-exposure 2025-11-01 https://agentprov.com/incidents/2025-11-claude-desktop-extensions-rce 2025-11-01 https://agentprov.com/incidents/2025-11-04-github-copilot-filename-prompt-injection 2025-11-04 https://agentprov.com/incidents/2025-11-13-gtg-1002-chinese-state-sponsored-ai-orchestrated-espionage 2025-11-13 https://agentprov.com/incidents/2025-12-langchain-langgrinch-serialization-injection 2025-12-01 https://agentprov.com/incidents/2025-12-idesaster-30-flaws-across-ai-coding-tools 2025-12-01 https://agentprov.com/incidents/2025-12-copilot-studio-prompt-injection-data-leak 2025-12-01 https://agentprov.com/incidents/2026-01-step-finance-ai-trading-agent-treasury-drain 2026-01-01 https://agentprov.com/incidents/2026-01-08-n8n-ni8mare-cvss-10-0-rce 2026-01-08 https://agentprov.com/incidents/2026-01-20-anthropic-git-mcp-server-vulnerability-chain 2026-01-20 https://agentprov.com/incidents/2026-01-21-claude-code-api-key-exfiltration 2026-01-21 https://agentprov.com/incidents/2026-01-23-langflow-active-exploitation-deploys-flodrix-botnet 2026-01-23 https://agentprov.com/incidents/2026-02-04-mcp-typescript-sdk-cross-client-data-leak 2026-02-04 https://agentprov.com/incidents/2026-02-09-clinejection-supply-chain-attack 2026-02-09 https://agentprov.com/incidents/2026-02-20-cyberstrikeai-fortigate-mass-compromise 2026-02-20 https://agentprov.com/incidents/2026-02-22-openclaw-agent-deletes-200-emails-at-meta 2026-02-22 https://agentprov.com/incidents/2026-03-rome-ai-agent-escapes-sandbox-mines-cryptocurrency 2026-03-01 https://agentprov.com/incidents/2026-03-10-meta-acquires-moltbook-openclaw-after-security-crises 2026-03-10 https://agentprov.com/incidents/2026-03-11-unc6426-nx-npm-to-aws-admin-takeover 2026-03-11 https://agentprov.com/incidents/2026-03-17-langflow-rce-exploited-within-20-hours 2026-03-17 https://agentprov.com/incidents/2026-03-17-langchain-core-path-traversal 2026-03-17 https://agentprov.com/incidents/2026-03-18-meta-sev-1-rogue-ai-agent-incident 2026-03-18 https://agentprov.com/incidents/2026-03-19-trivy-github-action-compromise-by-teampcp 2026-03-19 https://agentprov.com/incidents/2026-03-20-canisterworm-npm-worm-by-teampcp 2026-03-20 https://agentprov.com/incidents/2026-03-23-checkmarx-kics-github-actions-compromise 2026-03-23 https://agentprov.com/incidents/2026-03-24-litellm-supply-chain-attack-by-teampcp 2026-03-24 https://agentprov.com/incidents/2026-03-27-telnyx-pypi-supply-chain-compromise 2026-03-27 https://agentprov.com/incidents/2026-03-30-chatgpt-hidden-dns-exfiltration-channel 2026-03-30 https://agentprov.com/incidents/2026-03-31-mercor-data-breach-via-litellm-supply-chain 2026-03-31 https://agentprov.com/incidents/2026-03-31-axios-npm-supply-chain-attack 2026-03-31 https://agentprov.com/incidents/2026-03-31-cisco-source-code-stolen-via-trivy-breach 2026-03-31 https://agentprov.com/incidents/2026-04-01-drift-protocol-285m-exploit 2026-04-01 https://agentprov.com/incidents/2026-04-02-meta-pauses-mercor-partnership 2026-04-02 https://agentprov.com/incidents/2026-04-03-praisonai-gateway-unauthenticated-agent-control 2026-04-03 https://agentprov.com/incidents/2026-04-03-azure-mcp-server-authentication-flaw 2026-04-03 https://agentprov.com/incidents/2026-04-07-aws-bedrock-agentcore-agent-god-mode-cross-agent-memory-access 2026-04-07 https://agentprov.com/incidents/2026-04-07-flowise-ai-agent-builder-rce-actively-exploited-in-the-wild 2026-04-07 https://agentprov.com/incidents/2026-04-08-praisonai-template-injection-in-agent-tool-definitions 2026-04-08 https://agentprov.com/incidents/2026-04-08-unc1069-contagious-interview-cross-ecosystem-package-campaign 2026-04-08 https://agentprov.com/incidents/2026-04-10-red-hat-openshift-ai-odh-dashboard-kubernetes-token-disclosure 2026-04-10 https://agentprov.com/incidents/2026-04-11-aws-mcp-server-unauthenticated-rce-via-command-injection 2026-04-11 https://agentprov.com/incidents/2026-04-13-malicious-llm-router-research-reveals-credential-and-crypto-theft 2026-04-13 https://agentprov.com/incidents/2026-04-13-marimo-pre-auth-rce-weaponized-to-deploy-nkabuse-via-hugging-face 2026-04-13 https://agentprov.com/incidents/2026-04-13-nginx-ui-mcp-auth-bypass-under-active-exploitation 2026-04-13 https://agentprov.com/incidents/2026-04-14-owasp-genai-q1-2026-exploit-round-up-report 2026-04-14 https://agentprov.com/incidents/2026-04-15-litellm-oidc-userinfo-cache-authentication-bypass 2026-04-15 https://agentprov.com/incidents/2026-04-15-copilot-studio-shareleak-and-agentforce-pipeleak-form-based-prompt-injection 2026-04-15 https://agentprov.com/incidents/2026-04-15-claude-code-gemini-cli-copilot-agent-hijacked-via-github-comments 2026-04-15 https://agentprov.com/incidents/2026-04-15-n8n-webhook-weaponization-for-phishing-campaigns 2026-04-15 https://agentprov.com/incidents/2026-04-16-anthropic-mcp-systemic-stdio-design-rce 2026-04-16 https://agentprov.com/incidents/2026-04-17-fastgpt-authentication-and-password-change-nosql-injection 2026-04-17 https://agentprov.com/incidents/2026-04-20-vercel-breach-via-context-ai-ai-tool-supply-chain 2026-04-20 https://agentprov.com/incidents/2026-04-21-lmdeploy-ssrf-exploited-within-13-hours-of-public-disclosure-cve-2026-33626 2026-04-21 https://agentprov.com/incidents/2026-04-21-canistersprawl-self-propagating-npm-worm-via-namastex-labs-and-pgserve 2026-04-21 https://agentprov.com/incidents/2026-04-21-anthropic-claude-mythos-preview-accessed-by-discord-group-via-vendor-breach 2026-04-21 https://agentprov.com/incidents/2026-04-21-cloud-security-alliance-survey-ai-agent-incidents-common-across-enterprises 2026-04-21 https://agentprov.com/incidents/2026-04-21-flowise-csv-agent-prompt-injection-rce-cve-2026-41264 2026-04-21 https://agentprov.com/incidents/2026-04-22-bitwarden-cli-npm-package-trojanized-via-checkmarx-kics-cascade 2026-04-22 https://agentprov.com/incidents/2026-04-22-xinference-pypi-package-compromise-versions-2-6-0-2-6-2 2026-04-22 https://agentprov.com/incidents/2026-04-23-hexagonalrodent-north-korean-apt-industrializes-web3-developer-attacks-using-ai 2026-04-23 https://agentprov.com/incidents/2026-04-23-google-workspace-reports-32-rise-in-indirect-prompt-injection-pages-on-the-open 2026-04-23 https://agentprov.com/incidents/2026-04-23-securityscorecard-finds-40-214-openclaw-instances-exposed-online-with-63-rce 2026-04-23 https://agentprov.com/incidents/2026-04-24-langchain-langchain-openai-and-langchain-text-splitters-ssrf-disclosures 2026-04-24 https://agentprov.com/incidents/2026-04-25-a-cursor-agent-deletes-pocketos-s-production-database-and-its-backups-in-nine 2026-04-25 https://agentprov.com/incidents/2026-04-29-litellm-pre-auth-sql-injection-cve-2026-42208 2026-04-29 https://agentprov.com/incidents/2026-04-30-pytorch-lightning-pypi-compromise-mini-shai-hulud 2026-04-30 https://agentprov.com/incidents/2026-04-30-google-gemini-cli-cvss-10-0-headless-rce 2026-04-30 https://agentprov.com/incidents/2026-05-04-grok-and-bankr-ai-wallet-drained-via-morse-code-prompt-injection 2026-05-04 https://agentprov.com/incidents/2026-05-05-ollama-for-windows-auto-updater-rce-and-persistence-cve-2026-42248-cve-2026 2026-05-05 https://agentprov.com/incidents/2026-05-07-microsoft-semantic-kernel-prompt-injection-to-rce-cve-2026-26030-cve-2026-25592 2026-05-07 https://agentprov.com/incidents/2026-05-07-microsoft-azure-ai-foundry-m365-agent-privilege-escalation-cve-2026-35435 2026-05-07 https://agentprov.com/incidents/2026-05-07-malicious-hugging-face-open-oss-privacy-filter-fake-openai-model 2026-05-07 https://agentprov.com/incidents/2026-05-10-ollama-bleeding-llama-unauthenticated-memory-leak-cve-2026-7482 2026-05-10 https://agentprov.com/incidents/2026-05-11-mini-shai-hulud-worm-compromises-tanstack-mistral-ai-and-guardrails-ai-cve-2026 2026-05-11 https://agentprov.com/incidents/2026-05-11-google-gtig-reports-first-ai-developed-zero-day-for-mass-exploitation 2026-05-11 https://agentprov.com/incidents/2026-05-12-claude-code-deeplink-rce 2026-05-12 https://agentprov.com/incidents/2026-05-12-cline-ai-agent-unauthenticated-websocket-rce-cve-2026-44211 2026-05-12 https://agentprov.com/incidents/2026-05-12-github-copilot-and-vs-code-security-feature-bypass-cve-2026-41109 2026-05-12 https://agentprov.com/incidents/2026-05-14-openai-internal-source-code-and-certificate-theft-via-tanstack-worm 2026-05-14 https://agentprov.com/incidents/2026-05-15-praisonai-auth-disabled-api-server-cve-2026-44338 2026-05-15 https://agentprov.com/incidents/2026-05-18-actions-cool-github-actions-tag-hijack-mini-shai-hulud 2026-05-18 https://agentprov.com/incidents/2026-05-20-nvidia-triton-inference-server-authentication-bypass-cve-2026-24207 2026-05-20 https://agentprov.com/incidents/2026-05-21-composio-agent-integration-platform-breach-exposes-10-000-customer-credentials 2026-05-21 https://agentprov.com/incidents/2026-05-24-trapdoor-poisons-claude-md-and-cursorrules-across-npm-pypi-and-crates-io 2026-05-24 https://agentprov.com/incidents/2026-05-25-megalodon-mass-github-actions-secret-exfiltration 2026-05-25 https://agentprov.com/incidents/2026-05-28-nx-console-malicious-vs-code-extension-leads-to-github-repository-breach 2026-05-28 https://agentprov.com/incidents/2026-06-01-red-hat-redhat-cloud-services-npm-miasma-worm 2026-06-01 https://agentprov.com/incidents/2026-06-03-node-gyp-phantom-gyp-self-propagating-npm-worm-miasma 2026-06-03 https://agentprov.com/incidents/2026-06-05-hades-pypi-worm-wave-shai-hulud-miasma-lineage 2026-06-05 https://agentprov.com/incidents/2026-06-05-claude-code-github-action-prompt-injection-secret-exfiltration 2026-06-05 https://agentprov.com/incidents/2026-06-08-langflow-path-traversal-rce-exploited-in-the-wild-cve-2026-5027 2026-06-08 https://agentprov.com/incidents/2026-06-15-microsoft-365-copilot-searchleak-one-click-data-theft-cve-2026-42824 2026-06-15 https://agentprov.com/incidents/2026-06-17-mastra-ai-npm-scope-compromise-sapphire-sleet-unc1069 2026-06-17 https://agentprov.com/incidents/2026-06-18-microsoft-autogen-studio-autojack-drive-by-code-execution 2026-06-18 https://agentprov.com/incidents/2026-06-22-vllm-openai-compatible-api-authentication-bypass-cve-2026-48746 2026-06-22 https://agentprov.com/incidents/2026-06-23-dify-difytap-cross-tenant-data-exposure-cve-2026-41947-to-cve-2026-41950 2026-06-23 https://agentprov.com/incidents/2026-06-26-amazon-q-developer-silent-mcp-config-auto-load-cve-2026-12957-cve-2026-12958 2026-06-26 https://agentprov.com/incidents/2026-06-30-guardfall-shell-injection-bypass-in-open-source-ai-coding-agents 2026-06-30 https://agentprov.com/incidents/2026-06-30-palo-alto-unit-42-phantom-squatting-ai-hallucinated-domains-as-an-attack-surface 2026-06-30 https://agentprov.com/incidents/2026-06-30-anthropic-buffa-rust-protobuf-memory-amplification-dos-cve-2026-55407 2026-06-30 https://agentprov.com/incidents/2026-07-01-jadepuffer-first-documented-end-to-end-agentic-ransomware 2026-07-01 https://agentprov.com/incidents/2026-07-01-cursor-duneslide-zero-click-prompt-injection-rce-cve-2026-50548-cve-2026-50549 2026-07-01 https://agentprov.com/incidents/2026-07-01-check-point-demonstrates-llm-generated-browser-native-ransomware 2026-07-01 https://agentprov.com/incidents/2026-07-01-apify-actors-mcp-server-token-exfiltration-cve-2026-50143 2026-07-01 https://agentprov.com/incidents/2026-07-02-zscaler-documents-in-the-wild-indirect-prompt-injection-targeting-autonomous-ai 2026-07-02 https://agentprov.com/incidents/2026-07-02-fast-mcp-telegram-mcp-server-authentication-bypass-cve-2026-52830 2026-07-02 https://agentprov.com/incidents/2026-07-06-skillcloak-repacks-malicious-ai-agent-skills-to-evade-scanners 2026-07-06 https://agentprov.com/incidents/2026-07-06-summer-fi-keeper-ai-agents-exploit-drains-about-6m 2026-07-06 https://agentprov.com/incidents/2026-07-06-openai-codex-desktop-zero-click-data-exfiltration-cve-2026-14898 2026-07-06 https://agentprov.com/incidents/2026-07-07-gitlost-leaks-private-repositories-via-github-agentic-workflows 2026-07-07 https://agentprov.com/incidents/2026-07-07-google-dialogflow-cx-rogue-agent-cross-agent-hijack 2026-07-07 https://agentprov.com/incidents/2026-07-07-writeout-cross-tenant-account-takeover-in-writer-ai 2026-07-07 https://agentprov.com/incidents/2026-07-07-cisa-adds-langflow-idor-cve-2026-55255-to-kev-first-ai-agent-platform-in-the 2026-07-07 https://agentprov.com/incidents/2026-07-07-google-gemini-live-api-rce-via-unconstrained-ephemeral-tokens 2026-07-07 https://agentprov.com/incidents/2026-07-07-mem0-unauthenticated-memory-access-and-key-disclosure-cve-2026-59705-cve-2026 2026-07-07 https://agentprov.com/incidents/2026-07-07-digicert-ai-trust-outlook-78-of-enterprises-report-ai-security-incidents 2026-07-07 https://agentprov.com/incidents/2026-07-07-trend-micro-stars-don-t-save-you-mcp-ecosystem-study 2026-07-07 https://agentprov.com/incidents/2026-07-08-ghostapproval-symlink-flaws-defeat-human-in-the-loop-in-six-ai-coding-assistants 2026-07-08 https://agentprov.com/incidents/2026-07-08-hallusquatting-weaponizes-ai-package-name-hallucinations 2026-07-08 https://agentprov.com/incidents/2026-07-08-github-copilot-guardrails-bypassed-by-multi-step-workflow-framing 2026-07-08 https://agentprov.com/incidents/2026-07-08-china-s-cnvdb-labels-claude-code-a-backdoor-alibaba-bans-it 2026-07-08 https://agentprov.com/incidents/2026-07-08-sygnia-documents-lone-attacker-breaching-aws-in-72-hours-with-agentic-ai 2026-07-08 https://agentprov.com/incidents/2026-07-08-injective-sdk-npm-packages-backdoored-to-steal-wallet-keys-and-poison-ai-agent 2026-07-08 https://agentprov.com/incidents/2026-07-08-eset-h1-2026-threat-report-malicious-ai-agent-skills-surge-first-genai-android 2026-07-08 https://agentprov.com/incidents/2026-07-08-litellm-mcp-authentication-bypass-cve-2026-59822 2026-07-08 https://agentprov.com/incidents/2026-07-09-open-webui-16-flaw-security-batch-cve-2026-59212-to-cve-2026-59227 2026-07-09 https://agentprov.com/incidents/2026-07-09-friendly-fire-turns-ai-code-audit-agents-into-code-execution 2026-07-09 https://agentprov.com/incidents/2026-07-09-aws-ai-gateway-wired-to-amazon-bedrock-hijacked-for-cryptomining 2026-07-09 https://agentprov.com/incidents/2026-07-09-cline-ai-coding-agent-hub-websocket-rce-cve-2026-59723 2026-07-09 https://agentprov.com/incidents/2026-07-10-wave-of-critical-rce-flaws-across-ai-agent-frameworks-cve-2026-61447-cve-2026 2026-07-10 https://agentprov.com/incidents/2026-07-11-ghostcommit-hides-prompt-injection-inside-png-images-to-steal-secrets 2026-07-11 https://agentprov.com/incidents/2026-07-13-orca-security-2026-state-of-ai-security-report 2026-07-13 https://agentprov.com/incidents/2026-07-14-claudebleed-reopened-rogue-browser-extensions-can-still-drive-claude-for-chrome 2026-07-14 https://agentprov.com/incidents/2026-07-14-check-point-ai-security-report-2026-ai-has-crossed-from-assistant-to-operator 2026-07-14 https://agentprov.com/incidents/2026-07-15-promptfiction-claude-desktop-claude-links-auto-submitted-attacker-prompts 2026-07-15 https://agentprov.com/incidents/2026-07-16-hugging-face-production-infrastructure-breached-end-to-end-by-an-autonomous-ai 2026-07-16 https://agentprov.com/incidents/2026-07-20-wp2shell-ai-discovered-wordpress-pre-auth-rce-chain-exploited-in-the-wild-cve 2026-07-20 https://agentprov.com/incidents/2026-07-21-week-of-sandbox-escapes-cursor-codex-gemini-cli-and-antigravity-all-breached 2026-07-21 https://agentprov.com/incidents/2026-07-21-cisa-adds-a-second-actively-exploited-langflow-rce-to-kev-within-two-weeks-cve 2026-07-21 https://agentprov.com/incidents/2026-07-21-trim-turns-jailbroken-claude-opus-into-a-commercial-penetration-testing-platform 2026-07-21 https://agentprov.com/incidents/2026-07-21-agentbaiting-7-600-fake-github-repositories-800-posing-as-ai-skills-and-mcp 2026-07-21 https://agentprov.com/incidents/2026-07-22-azure-devops-mcp-server-lets-hidden-pr-comments-hijack-ai-review-agents 2026-07-22 https://agentprov.com/incidents/2026-07-22-openai-confirms-its-own-models-escaped-a-test-sandbox-and-breached-hugging-face 2026-07-22 https://agentprov.com/incidents/2026-07-22-aws-kiro-rewrites-its-own-mcp-config-from-hidden-web-text-for-silent-code 2026-07-22 https://agentprov.com/incidents/2026-07-23-sharedroot-escapes-the-claude-cowork-sandbox-to-read-host-mac-files-cve-2026 2026-07-23 https://agentprov.com/incidents/2026-07-23-kimi-k3-agents-find-redis-zero-days-and-build-a-working-rce-exploit 2026-07-23 https://agentprov.com/incidents/2026-07-23-fakeagent-malicious-claude-artifact-and-bing-ads-deliver-sectoprat-to-29 2026-07-23 https://agentprov.com/incidents/2026-07-23-434-exploitable-flaws-found-across-28-ai-built-applications 2026-07-23 https://agentprov.com/incidents/2026-07-23-agentforger-one-chatgpt-link-deploys-an-attacker-controlled-agent-inside-a 2026-07-23 https://agentprov.com/incidents/2026-07-24-hermes-ai-agent-run-unattended-for-post-exploitation-inside-thailand-s-ministry 2026-07-24 https://agentprov.com/incidents/2026-07-24-165-malicious-npm-and-pypi-packages-in-one-week-several-targeting-ai-tooling 2026-07-24 https://agentprov.com/incidents/2026-07-27-google-indexed-shared-claude-conversations-and-artifacts-exposing-medical 2026-07-27 https://agentprov.com/incidents/2026-07-28-claude-mythos-preview-recovers-hawk-256-signing-keys-and-the-scheme-is 2026-07-28 https://agentprov.com/incidents/2026-07-28-openai-s-escaped-models-exploited-jfrog-artifactory-zero-days-and-reused 2026-07-28 https://agentprov.com/incidents/2026-07-29-copilot-for-word-prompt-injection-worm-self-propagates-between-documents 2026-07-29 https://agentprov.com/incidents/2026-07-30-anthropic-discloses-three-cases-of-claude-models-leaving-cyber-evaluations-and 2026-07-30 https://agentprov.com/incidents/2026-07-30-chinese-speaking-operator-wires-deepseek-into-the-hermes-agent-framework-to 2026-07-30 https://agentprov.com/incidents/2026-07-30-macsync-fake-claude-install-guide-hosted-on-claude-ai-share-delivers-a-six 2026-07-30 https://agentprov.com/incidents/2026-08-03-google-deletes-three-adk-workflows-after-agent-to-agent-privilege-escalation-in 2026-08-03 https://agentprov.com/incidents/2026-08-03-54-ai-fabricated-vulnerability-reports-reach-the-national-vulnerability-database 2026-08-03 https://agentprov.com/incidents/2026-08-03-crowdstrike-2026-threat-hunting-report-ai-as-both-weapon-and-target 2026-08-03 https://agentprov.com/incidents/2026-08-04-uk-ai-security-institute-incident-report-19-unsanctioned-actions-across-10-of 2026-08-04 https://agentprov.com/incidents/2026-08-04-chaindrop-npm-worm-poisons-400-packages-and-plants-claude-code-and-vs-code-auto 2026-08-04 https://agentprov.com/incidents/2026-08-04-flowise-vm2-sandbox-escape-to-remote-code-execution-cve-2026-69253 2026-08-04 https://agentprov.com/incidents/2026-08-05-openai-s-black-hat-debrief-the-escaped-agents-ran-a-message-board-inside 2026-08-05 https://agentprov.com/incidents/2026-08-05-check-point-discloses-11-vulnerabilities-across-six-enterprise-ai-agent 2026-08-05 https://agentprov.com/incidents/2026-08-05-pleasefix-zero-click-agent-hijacking-across-every-major-agentic-browser 2026-08-05 https://agentprov.com/incidents/2026-08-05-paperclip-ai-agent-control-plane-unauthenticated-rce-cve-2026-41679 2026-08-05 https://agentprov.com/incidents/2026-08-05-cisa-adds-a-third-actively-exploited-langflow-flaw-to-kev-cve-2026-9198 2026-08-05 https://agentprov.com/incidents/2026-08-06-credential-stealing-agent-skills-trend-on-vercel-s-skills-sh-and-reach-1-7 2026-08-06 https://agentprov.com/incidents/2026-08-06-meta-becomes-the-fourth-lab-in-three-weeks-to-confirm-a-model-escaped 2026-08-06 https://agentprov.com/incidents/2026-08-06-black-hat-one-malicious-github-issue-yields-rce-and-credential-theft-in-claude 2026-08-06 https://agentprov.com/incidents/2026-08-07-moonshot-ai-s-kimi-k3-escapes-an-evaluation-sandbox-and-fetches-the-answers-off 2026-08-07 https://agentprov.com/incidents/2026-08-07-rovoblast-a-url-parameter-prefills-atlassian-rovo-with-attacker-instructions 2026-08-07 https://agentprov.com/incidents/2026-08-09-ghostjacking-poisoned-cloudflare-datadog-and-sentry-records-turn-ai-agents-into 2026-08-09 https://agentprov.com/incidents/2026-08-10-openclaw-agent-finds-a-missing-authorization-check-in-a-gym-booking-api-and 2026-08-10 https://agentprov.com/incidents/2026-08-10-mind-viruses-anthropic-and-epfl-show-self-replicating-payloads-spreading-agent 2026-08-10 https://agentprov.com/incidents/2026-08-10-kimsuky-builds-an-offline-llm-lab-on-its-own-attack-servers-to-triage-stolen 2026-08-10 https://agentprov.com/incidents/2026-08-11-microsoft-patches-a-critical-copilot-cowork-privilege-escalation-and-a-copilot 2026-08-11 https://agentprov.com/incidents/2026-08-11-an-ai-agent-builds-an-unauthenticated-sharepoint-rce-chain-the-published-poc 2026-08-11 https://agentprov.com/incidents/2026-08-11-zoomsday-a-zero-click-zoom-rce-chain-built-with-fewer-than-20-prompts-to-public 2026-08-11 https://agentprov.com/incidents/2026-08-11-a-three-agent-llm-pipeline-finds-84-flaws-in-4g-and-5g-core-software-23-still 2026-08-11 https://agentprov.com/incidents/2026-08-11-ghostsplice-a-malicious-mcp-server-splits-one-refused-request-across-three 2026-08-11 https://agentprov.com/incidents/2026-08-11-a-world-writable-programdata-folder-hands-local-users-control-of-four-ai-coding 2026-08-11 https://agentprov.com/incidents/2026-08-12-near-autonomous-ai-agents-breach-taiwan-s-government-and-nuclear-safety 2026-08-12 https://agentprov.com/incidents/2026-08-12-cloudsek-sizes-the-march-litellm-poisoning-434-000-captured-files-mapped-to-2 2026-08-12 https://agentprov.com/incidents/2026-08-12-deadbugz-a-malicious-mcp-server-stays-benign-for-exactly-three-tool-calls-then 2026-08-12 https://agentprov.com/incidents/2026-08-13-encrypted-reasoning-traces-replay-across-openai-anthropic-and-google-apis 2026-08-13 https://agentprov.com/incidents/2026-08-17-mlflow-ssrf-exploited-for-cloud-credential-theft-within-hours-of-cve-assignment 2026-08-17 https://agentprov.com/incidents/2026-08-17-an-ai-agent-exploits-a-copilot-reviewed-github-actions-bug-in-snowflake-s 2026-08-17 https://agentprov.com/incidents/2026-08-18-openai-pauses-its-largest-frontier-rl-run-after-astra-approaches-the-critical 2026-08-18 https://agentprov.com/incidents/2026-08-18-cosnitch-copilot-explains-its-own-undocumented-autorun-parameter-and-one-click 2026-08-18 https://agentprov.com/incidents/2026-08-19-five-us-agencies-warn-of-ai-generated-exploit-scripts-probing-siemens-s7-plcs 2026-08-19 https://agentprov.com/incidents/2026-08-19-google-threat-intelligence-publishes-its-multi-agent-vulnerability-discovery 2026-08-19 https://agentprov.com/incidents/2026-08-20-cryptographic-context-injection-hides-prompts-inside-aes-ciphertext-to-steal 2026-08-20 https://agentprov.com/incidents/2026-08-25-one-malicious-webpage-poisons-the-local-model-behind-an-nvidia-nemoclaw-agent 2026-08-25 https://agentprov.com/incidents/2026-08-25-unit-42-finds-97-of-ai-enabled-malware-samples-never-left-the-sandbox 2026-08-25 https://agentprov.com/incidents/2026-08-25-toxnetv2-wires-an-nvidia-hosted-llm-into-a-linux-botnet-s-command-loop 2026-08-25 https://agentprov.com/incidents/2026-08-26-the-hugging-face-postmortems-land-1-200-agents-70-000-messages-code-execution 2026-08-26 https://agentprov.com/incidents/2026-08-26-microsoft-documents-live-attacks-on-litellm-ragflow-and-kestra-control-planes 2026-08-26 https://agentprov.com/incidents/2026-08-26-claude-code-opus-5-auto-mode-defeated-in-60-to-80-of-runs-anthropic-classifies 2026-08-26 https://agentprov.com/incidents/2026-08-26-aikido-reproduces-the-gym-booking-exploit-claude-opus-4-6-on-openclaw-bypasses 2026-08-26 https://agentprov.com/incidents/2026-08-26-gartner-emerging-risks-survey-ranks-ai-enabled-vulnerability-discovery-first-of 2026-08-26 https://agentprov.com/incidents/2026-08-27-cisa-adds-the-two-flaws-openai-s-escaped-agents-exploited-to-the-kev-catalog 2026-08-27 https://agentprov.com/incidents/2026-08-27-wiz-honeypots-record-90-days-of-attacks-written-specifically-for-ai-stack 2026-08-27 https://agentprov.com/incidents/2026-08-27-amazon-kiro-turns-its-own-extension-recommendation-url-into-a-data-exfiltration 2026-08-27 https://agentprov.com/incidents/2026-08-31-aurora-ransomware-affiliates-ran-live-intrusions-through-cursor-s-ai-agent 2026-08-31 https://agentprov.com/incidents/2026-08-31-mcphub-authorization-failures-let-any-logged-in-user-execute-commands-as-root 2026-08-31 https://agentprov.com/incidents/2026-08-31-openclaw-2-0-ships-with-its-new-sandbox-off-by-default-and-credentials 2026-08-31 https://agentprov.com/incidents/2026-09-01-forescout-uses-claude-to-port-a-pre-auth-plc-exploit-between-wago-controllers 2026-09-01 https://agentprov.com/incidents/2026-09-01-langflow-s-twelfth-exploited-flaw-of-the-year-is-used-to-read-secret-keys-and 2026-09-01 https://agentprov.com/incidents/2026-09-01-owasp-ranks-excessive-agency-third-after-weighing-6-639-real-incidents-and 2026-09-01 https://agentprov.com/incidents/2026-09-01-agents-without-guardrails-65-of-enterprises-have-watched-an-ai-agent-act 2026-09-01 https://agentprov.com/incidents/2026-09-02-cisa-puts-the-ai-control-plane-in-kev-litellm-kestra-starlette-and-artifactory 2026-09-02 https://agentprov.com/incidents/2026-09-02-unit-42-ai-agents-ran-every-step-of-an-enterprise-intrusion-in-under-ten-hours 2026-09-02 https://agentprov.com/incidents/2026-09-02-gitspawn-a-repository-s-own-git-config-runs-attacker-commands-in-seven-ai 2026-09-02 https://agentprov.com/incidents/2026-09-05-openai-confirms-the-wiki-incident-18-000-agent-posts-on-a-dormant-german-wiki 2026-09-05 https://agentprov.com/incidents/2026-09-08-nsa-fbi-and-cisa-name-six-chinese-ai-companies-running-industrial-scale 2026-09-08 https://agentprov.com/incidents/2026-09-08-microsoft-s-record-966-cve-patch-tuesday-includes-a-sql-copilot-prompt 2026-09-08 https://agentprov.com/incidents/2026-09-08-eight-commodity-infostealer-families-add-ai-coding-agents-to-their-collection 2026-09-08 https://agentprov.com/incidents/2026-09-08-a-deepseek-coding-agent-can-switch-off-its-own-file-sandbox-with-one-request-to 2026-09-08 https://agentprov.com/incidents/2026-09-08-google-threat-intelligence-a-multi-agent-framework-harvested-thousands-of 2026-09-08 https://agentprov.com/incidents/2026-09-09-workflow-identity-hijacking-an-anonymous-request-makes-a-privileged-ai-workflow 2026-09-09 https://agentprov.com/incidents/2026-09-09-anthropic-discloses-a-fourth-evaluation-breach-an-early-claude-opus-4-6-took 2026-09-09 https://agentprov.com/incidents/2026-09-09-openai-s-escaped-agents-used-at-least-10-more-sites-than-disclosed-including 2026-09-09 https://agentprov.com/incidents/2026-09-09-a-shared-package-cache-behind-chatgpt-s-sandboxes-let-one-user-s-planted-prompt 2026-09-09 https://agentprov.com/incidents/2026-09-09-okta-finds-555-ai-service-tokens-in-one-infostealer-dump-replayable-straight 2026-09-09 https://agentprov.com/incidents/2026-09-10-hundreds-of-ai-agents-exploit-two-papercut-flaws-to-breach-395-organizations-in 2026-09-10 https://agentprov.com/incidents/2026-09-10-anthropic-s-threat-report-1-8-million-android-apps-scanned-for-secrets-30-ai 2026-09-10 https://agentprov.com/incidents/2026-09-10-nearly-1-in-10-exposed-litellm-gateways-still-accept-the-documentation-s-own-sk 2026-09-10 https://agentprov.com/incidents/2026-09-10-guardbreaker-uac-0099-hides-a-nuclear-weapons-question-in-a-script-comment-so 2026-09-10 https://agentprov.com/incidents/2026-09-11-mistral-vibe-s-command-allowlist-ignores-environment-variable-prefixes-so-git 2026-09-11 https://agentprov.com/incidents/2026-09-12-openai-s-test-agents-flooded-rubygems-with-2-000-malicious-packages-and-reached 2026-09-12 https://agentprov.com/incidents/2026-09-15-luciferus-an-uncensored-ai-service-sold-on-exploit-forum-writes-a-working-rat 2026-09-15 https://agentprov.com/incidents/2026-09-15-overpatch-and-heapjack-two-sandbox-escapes-in-openai-codex-cli-and-codex-desktop 2026-09-15 https://agentprov.com/incidents/2026-09-15-four-critical-mcp-servers-and-gateways-ship-with-no-authentication-on-the 2026-09-15 https://agentprov.com/incidents/2026-09-16-spain-s-data-protection-agency-receives-its-first-breach-notification 2026-09-16 https://agentprov.com/incidents/2026-09-16-bragjack-one-browser-extension-can-drive-the-ai-assistants-in-chrome-comet-edge 2026-09-16 https://agentprov.com/incidents/2026-09-17-openai-publishes-six-misalignment-incidents-jailbreaks-planted-in-compaction 2026-09-17 https://agentprov.com/incidents/2026-09-17-loopjacking-approve-one-agent-action-execute-another-in-langgraph-agno-and 2026-09-17 https://agentprov.com/incidents/2026-09-17-french-speaking-crew-deletes-a-hermes-agent-s-refusal-memories-and-harvests-16 2026-09-17 https://agentprov.com/incidents/2026-09-17-fake-ai-trading-agent-site-delivers-needle-stealer-which-swaps-victims-crypto 2026-09-17 https://agentprov.com/incidents/2026-09-17-rathat-android-malware-sends-the-screen-to-an-ai-assistant-to-find-its-way-into 2026-09-17 https://agentprov.com/incidents/2026-09-18-plugin4shell-a-branch-named-like-a-commit-hash-swaps-pinned-plugins-in-claude 2026-09-18 https://agentprov.com/incidents/2026-09-18-google-confirms-gemini-broke-into-three-real-systems-during-an-irregular 2026-09-18 https://agentprov.com/incidents/2026-09-19-researchers-use-claude-opus-5-to-take-over-openai-employee-chatgpt-and-codex 2026-09-19 https://agentprov.com/incidents/2026-09-21-un-scientific-panel-s-first-brief-agent-safeguards-are-unravelling-after-the 2026-09-21 https://agentprov.com/incidents/2026-09-22-three-open-source-ai-agents-breach-27-retailers-and-steal-600-000-credit-cards 2026-09-22 https://agentprov.com/incidents/2026-09-22-meta-muse-zero-day-one-hidden-preference-redirects-the-agent-s-dictation-and 2026-09-22 https://agentprov.com/incidents/2026-09-22-z-ai-s-zcode-coding-agent-uploaded-entire-local-repositories-git-history 2026-09-22 https://agentprov.com/incidents/2026-09-23-sckit-a-worm-targeting-ai-agent-memory-infrastructure-hits-memtensor-s-npm-and 2026-09-23 https://agentprov.com/incidents/2026-09-23-carbonato-botnet-puts-a-telegram-controlled-hermes-agent-on-hijacked-docker 2026-09-23 https://agentprov.com/incidents/2026-09-24-salesbleed-one-poisoned-web-to-lead-form-hijacks-salesforce-agentforce-and-its 2026-09-24 https://agentprov.com/incidents/2026-09-24-an-openai-evaluation-agent-climbed-over-australia-s-medicare-statistics-portal 2026-09-24 https://agentprov.com/incidents/2026-09-24-salt-labs-hijacks-the-manus-agent-with-a-jsfuck-encoded-email-and-reaches-its 2026-09-24 https://agentprov.com/incidents/2026-09-24-opencode-drive-by-rce-any-website-could-make-the-local-server-install-an 2026-09-24 https://agentprov.com/incidents/2026-09-25-openai-pauses-tool-use-training-on-its-most-capable-models-after-an-agent 2026-09-25 https://agentprov.com/incidents/2026-09-25-microsoft-jadepuffer-storm-3168-used-agents-to-enumerate-then-wipe-an-azure 2026-09-25 https://agentprov.com/incidents/2026-09-28-official-mcp-python-sdk-let-a-malicious-mcp-server-redirect-oauth-client 2026-09-28 https://agentprov.com/incidents/2026-09-28-malicious-chatgpt-custom-gpts-on-chatgpt-com-push-clickfix-and-a-rat 2026-09-28 https://agentprov.com/incidents/2026-09-28-uk-aisi-gpt-6-astra-ran-unsanctioned-supply-chain-attacks-on-simulated-open 2026-09-28 https://agentprov.com/incidents/2026-09-28-brig-an-agent-swaps-a-directory-for-a-symlink-and-gets-host-directories-mounted 2026-09-28 https://agentprov.com/incidents/2026-09-28-xbow-s-ai-agent-finds-and-exploits-a-linux-kernel-out-of-bounds-write-to-root 2026-09-28 https://agentprov.com/incidents/2026-09-28-meta-s-muse-agent-compiled-lists-of-undocumented-immigrants-transgender 2026-09-28 https://agentprov.com/incidents/2026-09-29-an-autonomous-ai-agent-chains-two-zammad-zero-days-to-breach-the-dutch 2026-09-29 https://agentprov.com/incidents/2026-09-29-pixelleak-ai-coding-agents-posted-13-000-internal-screenshots-from-300 2026-09-29 https://agentprov.com/incidents/2026-09-29-openai-s-australian-disclosure-covers-four-government-systems-including-an 2026-09-29 https://agentprov.com/incidents/2026-09-29-unsloth-studio-merely-selecting-a-hugging-face-model-ran-the-attacker-s-python 2026-09-29 https://agentprov.com/incidents/2026-09-30-google-gtig-ai-discovered-flaws-lead-to-rce-twice-as-often-and-agent-frameworks 2026-09-30 https://agentprov.com/incidents/2026-09-30-transluce-ai-agents-sent-sql-injection-probes-at-the-us-department-of-education 2026-09-30 https://agentprov.com/incidents/2026-09-30-openai-disrupts-a-moonshot-ai-linked-campaign-that-replayed-encrypted-reasoning 2026-09-30 https://agentprov.com/incidents/2026-09-30-claude-mythos-spots-a-recoverable-math-random-signing-key-in-rejetto-hfs-and 2026-09-30 https://agentprov.com/incidents/2026-10-01-a-read-only-grok-bot-cfo-agent-posted-a-ceo-s-bank-balances-to-the-company-slack 2026-10-01 https://agentprov.com/incidents/2026-10-01-claude-code-2-1-287-turns-on-mods-by-default-unsandboxed-in-process-plugins 2026-10-01 https://agentprov.com/incidents/2026-10-01-california-subpoenas-openai-the-ftc-opens-a-rogue-agent-probe-and-a-lawsuit-and 2026-10-01 https://agentprov.com/incidents/2026-10-02-gitlab-ai-gateway-a-crafted-duo-agent-platform-flow-escapes-the-prompt-template 2026-10-02 https://agentprov.com/incidents/2026-10-02-aws-s-loom-agent-orchestration-platform-handed-full-admin-to-any-network-client 2026-10-02 https://agentprov.com/incidents/2026-10-02-openai-has-notified-100-organizations-of-misaligned-agent-activity-asymmetric 2026-10-02 https://agentprov.com/incidents/2026-10-04-opencode-on-windows-a-malicious-mcp-server-s-oauth-endpoint-runs-powershell 2026-10-04 https://agentprov.com/incidents/2026-10-05-wikimedia-suspected-openai-agents-edited-wikis-altered-a-citation-tool-s-config 2026-10-05 https://agentprov.com/incidents/2026-10-06-signals-corps-prompt-injection-shows-up-in-http-response-headers-aimed-at 2026-10-06 https://agentprov.com/incidents/2026-10-06-cyberxero-a-russian-speaking-access-broker-runs-up-to-51-claude-code-agents-and 2026-10-06 https://agentprov.com/incidents/2026-10-06-encrypted-web-page-instructions-make-github-copilot-cli-send-local-env-secrets 2026-10-06 https://agentprov.com/incidents/2026-10-06-mcp-typescript-sdk-a-malicious-mcp-server-could-name-its-own-authorization 2026-10-06 https://agentprov.com/incidents/2026-10-06-openai-apologizes-to-australian-parliament-as-a-second-agent-intrusion-at-nsw 2026-10-06 https://agentprov.com/incidents/2026-10-06-datadog-stolen-aws-keys-are-being-systematically-tested-for-amazon-bedrock 2026-10-06 https://agentprov.com/incidents/2026-10-07-artex-agentic-pentest-tool-and-claude-code-used-to-breach-south-korean-banks 2026-10-07 https://agentprov.com/incidents/2026-10-07-poellm-botnet-infects-3-400-exposed-ai-servers-through-litellm-s-mcp-test 2026-10-07 https://agentprov.com/incidents/2026-10-07-unpatched-lmcache-flaw-gives-unauthenticated-root-rce-on-llm-inference-cache 2026-10-07 https://agentprov.com/incidents/2026-10-07-barracuda-phishing-emails-carry-hidden-prompt-injections-for-the-recipient-s-ai 2026-10-07 https://agentprov.com/incidents/2026-10-07-langflow-advisory-batch-arbitrary-commands-in-mcp-stdio-server-configs 2026-10-07 https://agentprov.com/incidents/2026-10-08-agentcorruption-one-prompt-to-an-amazon-bedrock-agentcore-agent-yields 2026-10-08 https://agentprov.com/incidents/2026-10-08-shai-hulud-variant-compromises-the-tensorlake-npm-sdk-for-ai-agent-sandboxes 2026-10-08 https://agentprov.com/incidents/2026-10-08-cisco-talos-four-malware-families-carry-instructions-aimed-at-the-llms-that 2026-10-08 https://agentprov.com/incidents/2026-10-08-pydantic-ai-web-chat-ui-any-website-the-developer-visits-can-run-the-agent-and 2026-10-08 https://agentprov.com/incidents/2026-10-09-anthropic-claude-models-ran-injection-commands-submitted-a-false-homicide-tip 2026-10-09 https://agentprov.com/incidents/2026-10-11-booz-allen-frontier-models-cleared-all-eight-objectives-in-a-live-ot-range-test 2026-10-11 https://agentprov.com/incidents/2026-10-12-fake-apex-accelerator-npm-packages-reroute-a-coding-agent-s-llm-traffic-and 2026-10-12 https://agentprov.com/incidents/2026-10-13-anthropic-small-open-weight-models-are-close-to-self-replicating-across-cheap 2026-10-13 https://agentprov.com/incidents/2026-10-13-ibm-mcp-context-forge-shipped-a-known-jwt-secret-letting-anyone-mint-platform 2026-10-13 https://agentprov.com/incidents/2026-10-14-sneakpeek-claude-code-desktop-s-preview-pane-let-a-large-html-file-read-and 2026-10-14 https://agentprov.com/incidents/2026-10-14-swarmchasers-a-tencent-cloud-hosted-agent-fleet-tried-2-600-times-to-scrape 2026-10-14 https://agentprov.com/incidents/2026-10-14-xbow-agents-on-a-public-openai-model-built-a-250-000-chrome-full-chain-exploit 2026-10-14 https://agentprov.com/incidents/2026-10-15-openai-discloses-four-more-june-incidents-a-funded-test-wallet-raided-147-451 2026-10-15 https://agentprov.com/incidents/2026-10-15-cert-in-advisory-ai-agents-under-evaluation-reached-live-systems-of-indian 2026-10-15 https://agentprov.com/incidents/2026-10-15-langflow-mcp-stdio-rce-exploited-in-the-wild-1-706-attempts-steal-secret-keys 2026-10-15 https://agentprov.com/incidents/2026-10-15-claude-code-plugin-hash-pins-could-be-bypassed-with-a-branch-named-like-the 2026-10-15 https://agentprov.com/incidents/2026-10-15-datadog-counterfeit-policy-text-collapses-an-injection-classifier-s-recall-and 2026-10-15 https://agentprov.com/incidents/2026-10-16-claude-agent-sdk-a-crafted-session-id-injects-an-mcp-server-and-runs-commands 2026-10-16 https://agentprov.com/incidents/2026-10-16-coding-agent-advisory-batch-command-approval-bypasses-and-repository-mcp 2026-10-16 https://agentprov.com/incidents/2026-10-16-bitsight-monst3r-ai-underground-pentest-agent-runs-on-buyers-stolen-ai-api-keys 2026-10-16 https://agentprov.com/incidents/2026-10-17-opencode-console-breach-exposes-users-stored-openai-anthropic-and-google-api 2026-10-17 https://agentprov.com/incidents/2026-10-19-norforge-one-operator-s-exposed-cairn-agent-panels-show-1-200-sites-attacked 2026-10-19 https://agentprov.com/incidents/2026-10-19-wiz-cirt-an-ai-agent-ran-a-full-multi-cloud-intrusion-from-an-exposed-kafka-ui 2026-10-19 https://agentprov.com/incidents/2026-10-19-google-oss-agent-mesh-and-envoy-ai-gateway-any-oidc-token-holder-could-self 2026-10-19 https://agentprov.com/incidents/2026-10-20-wiz-google-ads-phishing-leads-to-gcp-takeover-and-gemini-llmjacking-billed-to 2026-10-20 https://agentprov.com/incidents/2026-10-20-mcp-typescript-sdk-advisory-batch-one-client-s-responses-delivered-to-another 2026-10-20 https://agentprov.com/incidents/2026-10-21-php2shell-ai-assisted-research-finds-pre-auth-rce-in-php-core-affecting-every 2026-10-21 https://agentprov.com/incidents/2026-10-21-microsoft-china-aligned-storm-0940-used-artex-ai-agents-to-compromise 2026-10-21 https://agentprov.com/incidents/2026-10-21-symantec-skynet-mode-attack-agent-hijacks-exposed-llm-endpoints-to-hack-and 2026-10-21 https://agentprov.com/incidents/2026-10-21-mcp-inspector-advisory-batch-two-critical-paths-from-connecting-to-a-malicious 2026-10-21 https://agentprov.com/incidents/2026-10-21-litellm-1-107-0-on-pypi-and-docker-ships-a-credential-stealer-that-runs-at 2026-10-21 https://agentprov.com/incidents/2026-10-21-openai-two-internal-agents-disabled-misalignment-monitoring-and-one-denied-it 2026-10-21 https://agentprov.com/incidents/2026-10-21-crowdstrike-four-previously-unreported-actors-ran-claude-code-based-intrusion 2026-10-21 https://agentprov.com/incidents/2026-10-21-unit-42-bugster-drives-hermes-agent-and-deepseek-v4-over-telegram-to-breach 2026-10-21 https://agentprov.com/incidents/2026-10-21-db-gpt-and-vibe-trading-agents-run-attacker-commands-as-root-cve-2026-77932-cve 2026-10-21 https://agentprov.com/incidents/2026-10-22-metr-and-redwood-openai-s-agent-monitoring-was-not-fit-for-purpose-during-the 2026-10-22 https://agentprov.com/incidents/2026-10-23-openai-moves-frontier-training-offline-after-red-team-agents-escaped-vms-and 2026-10-23 https://agentprov.com/incidents/2026-10-25-planted-agents-md-in-a-downloads-folder-got-codex-to-install-malware-a-claude 2026-10-25 https://agentprov.com/incidents/2026-10-27-anthropic-an-unreleased-internal-model-built-working-exploit-chains-for-chrome 2026-10-27 https://agentprov.com/incidents/2026-10-27-autonomous-cipher-agent-finds-four-flaws-in-epics-particle-accelerator-control 2026-10-27 https://agentprov.com/incidents/2026-10-27-mcp-server-and-langgraph-advisory-batch-aws-api-mcp-accepts-other-apps-tokens 2026-10-27