2026-10-06 · 2026-Q4
Signals Corps: Prompt Injection Shows Up in HTTP Response Headers Aimed at Browsing Agents
Primary layerL2 Instruction
Who actually said "do this"?
- Fixable
- Architectural
- Vendor response
- Unknown
- In the wild
- Yes
- Actor
- Attacker
Target
AI agents that read raw HTTP response headers, such as through Playwright MCP's network request tool
Impact
Signals Corps scanned 217,097,223 Common Crawl HTTP responses and found 7,959 sites sending headers addressed to AI agents, 6,989 of them `x-llms-txt`. Thirty sites attempted indirect prompt injection, 22 of them apparently pranks, including a Claude refusal trigger string and a fake match-confidence value aimed at AI hiring screeners. In testing, Claude Code followed header instructions in 7 of 9 runs when the prompt framed the site as authoritative
Root cause
Agents ingest response metadata as context with the same trust as page content
Sources
Catalog
Cite this: AgentProv incident record: Signals Corps: Prompt Injection Shows Up in HTTP Response Headers Aimed at Browsing Agents (2026-10-06). https://agentprov.com/incidents/2026-10-06-signals-corps-prompt-injection-shows-up-in-http-response-headers-aimed-at
Related
- Also L2 · 2026-10-15Datadog: Counterfeit Policy Text Collapses an Injection Classifier's Recall and Pushes a LangChain Risk Gate Under Its Block ThresholdL2Instruction
- Also L2 · 2026-10-08Cisco Talos: Four Malware Families Carry Instructions Aimed at the LLMs That Triage ThemL2Instruction
- Also L2 · 2026-10-07Barracuda: Phishing Emails Carry Hidden Prompt Injections for the Recipient's AI Inbox AssistantL2Instruction