competitive-analyst

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md implementation and intelligence-gathering workflow explicitly instructs the agent to "Gather intelligence" from public information sources (e.g., "public information", "customer reviews", "social media presence", "news aggregation", "social listening", "patent watching") so the agent is expected to read and act on untrusted, user-generated or public third-party content as part of its analysis.