context7-auto-research

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

• Third-party content exposure detected (high risk: 0.80). The skill's main flow calls the context7-fetcher (context7-api.js) which makes HTTPS requests to https://context7.com/api/v2 to search and retrieve public documentation snippets that the agent directly reads and integrates into responses, so it ingests untrusted third-party content.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's runtime helper (context7-api.js) makes live API calls to https://context7.com/api/v2 and the returned documentation snippets are injected into the agent's responses at runtime, meaning external content from that URL directly controls what the agent outputs.