yt-shorts
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes video transcripts provided by the user or an external source, which represents an indirect prompt injection attack surface.
- Ingestion points: Video transcripts analyzed to identify "Shorts" (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or boundary markers to isolate the transcript data from the system instructions.
- Capability inventory: The skill performs text analysis and writing tasks only; it lacks network access, file system write permissions, and the ability to execute subprocesses or shell commands.
- Sanitization: There are no specific instructions to sanitize, escape, or filter the content of the transcript before processing.
Audit Metadata