transcript-intelligence
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data retrieved from video transcripts and metadata, creating a surface for potential indirect instructions.
- Ingestion points: External content enters the context through the
get_video_transcript,get_video, andget_channel_videostools, which fetch data from video platforms. - Boundary markers: The instructions lack specific delimiters or explicit guidelines for the agent to ignore any command-like text that may be embedded within the transcripts.
- Capability inventory: The skill is scoped to analysis and report generation in markdown; it does not have access to file-writing tools, shell execution, or arbitrary network capabilities.
- Sanitization: No sanitization or filtering logic is specified for the transcript text before it is joined and processed into the output report.
Audit Metadata