self-learning-feedback

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs "Use web search when external references improve correctness" (Why-How-What Resolution Requirement), so the agent will fetch and interpret public web content that could contain untrusted/user-generated instructions and materially influence its subsequent actions.