tldv

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly retrieves meeting recordings, transcripts, highlights, and AI-generated notes from the tl;dv REST API (see "Transcripts" and "Highlights / Notes" sections), which are user-generated third-party content the agent is expected to read and that could contain instructions influencing actions.