setup-context7-mcp

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (Step 2) explicitly directs the agent to load a public GitHub raw URL (https://raw.githubusercontent.com/upstash/context7/refs/heads/master/README.md) and to search Context7 MCP for documentation, meaning it fetches and interprets untrusted third-party content that can influence setup actions.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly instructs at runtime to load https://raw.githubusercontent.com/upstash/context7/refs/heads/master/README.md and use that fetched content to guide the setup (i.e., the external file directly controls agent instructions and is treated as a required dependency).