cookiy-workflows

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly reads participant-generated interview transcripts returned by cookiy_interview_playback_get (see references/ai-interview.md "View interview transcripts"), which are untrusted user-generated content the agent is required to read and that can influence follow-up workflow decisions like report generation or recruitment.