spec

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

• Third-party content exposure detected (high risk: 0.90). The skill's discovery and requirements phases (see rules/discovery.md and phases/requirements.md) explicitly instruct the agent to use external research tools (e.g., documentation lookup tools like "context7", web fetch tools "WebFetch", and web search "WebSearch") to read public documentation, blogs, and community forums — untrusted third‑party content that the agent must read and that can materially influence design and implementation decisions.