docs-seeker

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). At runtime, fetch-docs.js fetches readable llms.txt content from outsider-controlled public web sources (context7.com URLs constructed from the user query), and that fetched text is then piped into analyze-llms-txt.js via cat llms.txt | ..., so the agent’s LLM context can include outsider-authored free text.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The fetch-docs.js script performs runtime HTTPS GETs to context7.com (e.g., https://context7.com/{org}/{repo}/llms.txt[?topic=...]) and returns llms.txt content that is used to determine which documents/URLs agents will fetch and include in model context, meaning remote content from context7.com can directly control agent behavior.