risk-and-issues-manager-scott-margetts

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

• Third-party content exposure detected (high risk: 0.85). The skill’s REQUIRED runtime path for Mode 2/3 ingests user-provided email chains/meeting notes/call notes (outsider-authored free text from other participants) directly into the agent’s LLM context for decision/risk extraction.