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.md explicitly instructs the agent to "use web search to find recommendations specific to the codebase's tools, frameworks, and libraries" (Phase 1 / Output Guidelines), meaning the skill expects the agent to fetch and interpret open/public web content that could contain untrusted, user-generated instructions which may influence recommendations and follow-up actions.