context7-cli

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

• Third-party content exposure detected (low risk: 0.10). The skill fetches documentation and search results from Context7, which constitutes retrieved third-party library documentation/content rather than monitored unauthenticated outsider-authored feeds like issues or tickets.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to install and execute the ctx7 tool from npm (npm install -g ctx7@latest), which relies on an external package registry and lacks a URL locator establishing an official source.