context7-docs

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and returns library documentation from the public Context7 endpoints (e.g., the MCP fallback https://mcp.context7.com/mcp and direct REST https://context7.com/api/v2 as shown in SKILL.md and scripts/docs.sh), so untrusted third‑party docs are ingested and used in the agent's documentation lookup workflow and can influence subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill invokes "npx --yes mcporter" at runtime (which will fetch and execute the mcporter package from the npm registry, e.g. https://registry.npmjs.org/mcporter) and also makes runtime curl calls to https://mcp.context7.com/mcp and https://context7.com/api/v2 to fetch documentation that is injected into the agent's output, so it depends on and may execute remote code fetched at runtime.