c-level-advisor

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

• Third-party content exposure detected (medium risk: 0.30). In SKILL.md, outsider-authored free text enters at runtime via user-issued commands/questions (e.g., “Ask any strategic question” to Chief of Staff and directly prefixed role questions), which the router then routes for analysis—so the workflow ingests arbitrary user text.