meeting-minutes
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted data in the form of transcripts and chat logs, which creates a surface for indirect prompt injection.
- Ingestion points: Meeting transcripts, chat logs, and loose notes provided by the user (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or boundary markers to isolate the untrusted input from the system instructions.
- Capability inventory: The skill utilizes platform "document tools" to generate and output Word files.
- Sanitization: There are no explicit instructions for the agent to sanitize or escape potentially malicious instructions embedded within the user-provided text.
- [COMMAND_EXECUTION]: The skill instructions direct the agent to use "document tools available here" to generate a Word document, which typically involves generating and executing code or command-line utilities.
Audit Metadata