video-live
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted data from live video streams and meeting recordings, which could potentially contain instructions intended to influence the agent.
- Ingestion points: Meeting transcripts and video scene descriptions are ingested via get_transcript and get_rtstream_scenes in SKILL.md.
- Boundary markers: No explicit boundary markers or delimiters are defined to separate external content from agent instructions.
- Capability inventory: The skill possesses file-write capabilities (modifying .env files) and performs network operations using the VideoDB API and SDK.
- Sanitization: There are no explicit instructions for sanitizing or filtering the content retrieved from external sources before processing.
Audit Metadata