github

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

• Third-party content exposure detected (high risk: 0.90). This skill calls the GitHub MCP server (see SKILL.md and scripts/github.ts) and includes commands that fetch and read public, user-generated GitHub content — e.g., get-file-contents, search-code, get-pull-request-comments/files — which the agent is expected to interpret and could materially influence actions like reviews, comments, merges.

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

• Potentially malicious external URL detected (high risk: 0.90). The CLI launches "npx -y @modelcontextprotocol/server-github" at runtime (which pulls and runs the package from the npm registry, e.g. https://registry.npmjs.org/@modelcontextprotocol/server-github), so the skill fetches and executes remote code as a required runtime dependency.