transcript-to-content
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes meeting transcripts and recordings, creating a vulnerability surface where malicious instructions embedded in the data could influence agent actions. * Ingestion points: Reads raw meeting transcripts and training recordings from project directories. * Boundary markers: No specific delimiters or instructions are used to ensure transcript content is treated strictly as data. * Capability inventory: The skill uses
ls,grep,cp, and presentation editing tools to process and output data. * Sanitization: No explicit sanitization or escaping of transcript content is performed beyond removing conversational fillers. - [COMMAND_EXECUTION]: The skill utilizes standard shell utilities like
ls,grep, andcpfor searching and managing files within the project environment.
Audit Metadata