2025-01-24 · 2025-Q1

OmniGPT Data Breach

Primary layerL1 CredentialSecondary:L6 Identity / Run

Should this run hold this key at all?
The question layer 1 asks, and failed here.

Fixable: Unknown
Vendor response: Unknown
In the wild: Yes
Actor: Attacker

Target

OmniGPT AI aggregator

Impact

30K user emails/phones; 34M lines of chat messages leaked including API keys, crypto private keys

Root cause

Infrastructure breach; sold for $100 on BreachForums

Sources

Catalog

View this entry in the catalog

Cite this: AgentProv incident record: OmniGPT Data Breach (2025-01-24). https://agentprov.com/incidents/2025-01-24-omnigpt-data-breach

Also L1 · 2026-10-21LiteLLM 1.107.0 on PyPI and Docker Ships a Credential Stealer That Runs at Every Python StartupL1Credential
Also L1 · 2026-10-17OpenCode Console Breach Exposes Users' Stored OpenAI, Anthropic, and Google API KeysL1Credential
Also L1 · 2026-10-13IBM MCP Context Forge Shipped a Known JWT Secret, Letting Anyone Mint Platform Admin Tokens (CVE-2026-53709)L1Credential