yt-edit
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external transcript data from SRT, VTT, or JSON files.
- Ingestion point: The script reads user-provided transcript files via command-line arguments.
- Boundary markers: No delimiters are used to separate data from instructions.
- Capability inventory: The script is limited to read-only file access and console output, with no network or subprocess capabilities.
- Sanitization: No sanitization is performed on transcript text.
Audit Metadata