Research
Prompt injection in HTTP headers
First reported · Discovered signalscorps.com
Page published
Earliest dated coverage: 5 Oct 2026 · First observed: 15 Oct 2026 · Latest dated coverage: 5 Oct 2026
Coverage timeline
Single-source research — one report is available.
Why it matters
HTTP response headers are an injection channel that most prompt-injection defenses ignore, yet an agent's fetch tools can pass them straight to the model, so defenders must treat headers as untrusted content and monitor what agents do after a fetch.
Signals Corps analyzed HTTP response headers from 217 million page responses in Common Crawl's September 2026 crawl and found 7,959 sites sending headers aimed at AI systems, including 30 sites attempting prompt injection (24 in an 'X-AI' header, mostly pranks). The study notes headers are an under-researched injection route because browsers never display them, and tests showed Claude models in Claude Code surfaced the headers but did not act on them by default, obeying site directions in 7 of 9 runs only when the user's prompt granted the site authority.