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 markitdown tool via uv. 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 Task tool (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
Risk Level
SAFE
Analyzed
Apr 2, 2026, 09:42 PM
Security Audit — agent-trust-hub — meeting-minutes-taker