podcast-editor
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill provides technical guidelines for podcast editing. It references official documentation from well-known services (Apple, Spotify, and Google) for compliance and craft research.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data such as video transcripts and timeline metadata. This represents a standard attack surface for media processing skills; however, the skill uses structured instructional blocks (SPEC, DERIVE, CRAFT) to guide the agent, which helps mitigate accidental obedience to instructions embedded in transcripts.
- [COMMAND_EXECUTION]: The skill instructions reference specific video editing functions such as
switchAngle,cutRanges, andreframeAuto. These commands are consistent with the primary purpose of video and audio post-production and do not involve unauthorized system access.
Audit Metadata