interview

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

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 1 Preparation explicitly instructs the agent to "Read any referenced files or URLs provided by user" and to perform "Web Research (if applicable)" (SKILL.md, Phase 1), which requires fetching and interpreting potentially untrusted public URLs or user-provided web content that can materially influence the agent's subsequent questions and decisions.