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 explicitly constructs and retrieves documentation from public sites (e.g., context7.com) and outputs llms.txt for the agent to read (with instructions like "Read URLs with WebFetch"), so the agent will fetch and interpret untrusted third-party web content.