meeting-minutes-taker
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the user to install the
markitdowntool viauv. This tool is developed by a well-known service and is used for document conversion, which is a legitimate part of the skill's intended functionality. - [COMMAND_EXECUTION]: The workflow includes creating transcript-specific subdirectories and managing intermediate files using shell commands like
mkdir. These operations are localized to the output directory and support the multi-turn generation process. - [PROMPT_INJECTION]: The skill is identified as having a surface for indirect prompt injection (Category 8) because it processes untrusted meeting transcripts as primary input.
- Ingestion points: External meeting transcripts are loaded from the file system into the agent's context (referenced in SKILL.md).
- Boundary markers: The instructions do not currently specify the use of XML tags or other delimiters to isolate transcript content from the instructions provided to subagents.
- Capability inventory: The skill possesses file system write access and the ability to spawn subagents using the
Tasktool (SKILL.md). - Sanitization: There is no explicit logic to filter or sanitize the content of the transcript before it is processed by the AI.
Audit Metadata