profile-competitor

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime pipeline (Phase 2 researchers + Artifact Detection) is designed to ingest outsider-authored free text from public web sources (e.g., competitor pages/reviews/market sites) into the researchers’ LLM contexts via their “Source Triage Log”/“Cipher” evidence collection, which is then aggregated and reviewed by the Counter-Spy.