transcript-filing
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted transcript files to determine a topic-based folder name, which exposes the agent to instructions embedded within those files.
- Ingestion points: The agent reads the full content of a user-supplied file (e.g.,
docs/transcripts/transcript.txt) from the repository root. - Boundary markers: The instructions do not specify any delimiters or safety markers to isolate the transcript content from the agent's instructions, though it does explicitly state the agent should not extract claims.
- Capability inventory: The agent has the ability to read, move, and rename files, and create directories based on the results of its analysis of the transcript content.
- Sanitization: No sanitization or filtering is performed on the transcript data before it is processed for topic extraction.
Audit Metadata