transcript-purpose-analysis
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted transcript data, which presents a surface for indirect prompt injection if the source text contains instructions for the agent.
- Ingestion points: Transcript data is read from a user-supplied file path or inline text input (SKILL.md, Procedure Step 1).
- Boundary markers: The instructions do not specify explicit delimiters or "ignore previous instruction" warnings to be applied to the ingested transcript content.
- Capability inventory: The skill utilizes the agent's ability to read local repository files and write an analysis report to a new Markdown file (SKILL.md, Procedure Step 1, 5, and 7).
- Sanitization: No specific sanitization or filtering of the transcript text is performed, as the skill is required to extract verbatim quotes for evidence (SKILL.md, Output A).
Audit Metadata