show-notes-writer
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided transcripts and outlines to generate summaries and chapters.
- Ingestion points: The skill accepts transcripts or outlines as primary input in Step 1.
- Boundary markers: There are no explicit instructions to use delimiters or warnings for the agent to ignore embedded instructions within the transcript.
- Capability inventory: The skill has no access to sensitive tools, file system writes, or network operations.
- Sanitization: No specific sanitization or filtering of the transcript content is mentioned.
Audit Metadata