claude-automation-recommender

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to "use web search to find recommendations specific to the codebase" and to use MCPs like "context7" for live documentation lookup, which means it will fetch and read open/public third-party content (web pages/docs) that could contain untrusted, user-generated inputs.