docs-seeker

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

• Third-party content exposure detected (high risk: 0.90). The skill's fetch-docs.js and workflows explicitly fetch and ingest public llms.txt and documentation URLs from context7.com (and fall back to web searches, official sites, and public GitHub repositories) and then direct the agent to read those URLs (e.g., "Read URLs with WebFetch" and repository analysis steps), exposing the agent to untrusted third‑party content that could contain indirect prompt injections.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's runtime fetcher (fetch-docs.js) requests llms.txt from context7.com (e.g., https://context7.com/{org}/{repo}/llms.txt and https://context7.com/{org}/{repo}/llms.txt?topic=...) and the returned llms.txt is parsed and used to determine which URLs agents fetch and how agents are distributed, meaning external content directly controls agent behavior and is a required runtime dependency.