Prompt injection in HTTP headers: what 217M web responses show
Researchers analyzed over 200 million HTTP headers to identify potential prompt injection attacks aimed at AI agents. While most headers are benign, a small percentage contain malicious or deceptive instructions, highlighting a significant security vulnerability in how AI agents process web data.
Why it matters
As AI agents become more autonomous, the security of the data they ingest from the web becomes a critical vector for cyberattacks and system manipulation.
We scanned the HTTP headers of 217 million crawled web responses for text aimed at AI agents. Most point agents to llms.txt files and MCP servers, and 30 sites sent injection attempts.
We read the HTTP response headers of 217,097,223 page responses from Common Crawl, 10% of its September 2026 crawl of 2.17 billion pages, and looked for any header written for an AI system. 7,959 sites sent one. Almost all of them point agents to another resource, such as an llms.txt file or an MCP server. A small number try to give the agent orders. Whether any of it reaches your model depends on which parts of the response your fetch tool passes along, so the defense starts there.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in