marketing-agency

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly directs the agent to "audit" and use live websites or social/profile URLs as the immediate working context (see SKILL.md "Starting Context Router" and Step 1 — "If the user gave a live URL or profile, audit it first"), which requires fetching and interpreting public third‑party content that can materially influence decisions and actions.