meeting-to-tasks
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
BashandGreptools to process and search meeting transcript files. This is a standard use of these tools for text-based analysis within the agent's environment. - [PROMPT_INJECTION]: The skill processes untrusted external data in the form of meeting transcripts (text, markdown, and audio exports). This represents a potential surface for indirect prompt injection, where malicious instructions could be embedded in a transcript to influence agent behavior.
- Ingestion points: Meeting transcripts provided as files or pasted text.
- Boundary markers: The instructions do not specify explicit delimiters or boundary markers to separate transcript content from system instructions during processing.
- Capability inventory: The agent has access to
Read,Write,Bash, andGreptools. - Sanitization: No specific content sanitization is described beyond validating the length and presence of participants in the input.
Audit Metadata