personal-branding

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

• Third-party content exposure detected (medium risk: 0.30). In “Phase 1: Preparation” the orchestrator extracts “Career Information/Goals/Existing Materials” from the user’s free-text prompt and saves them into _workspace/00_input.md, which is then reviewed/used by downstream agents—so outsider-authored text is ingested and influences the workflow without selecting specific items first.