proof-of-concept

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

• Third-party content exposure detected (high risk: 0.80). The skill's required "Phase 1: Research" step explicitly instructs reading public third-party sources (e.g., official documentation, GitHub repositories, tutorial projects), meaning the agent is expected to ingest and act on untrusted, user-generated web content that can influence decisions and next actions.