meeting-minutes-taker
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted meeting transcripts and context files which could contain hidden instructions to override agent behavior. While inherent to the task, the skill lacks specific delimiters to separate untrusted data from instructions.
- Ingestion points: Meeting transcripts and user-provided project context files (e.g., context.md) used for speaker identification.
- Boundary markers: The prompt templates for subagents do not explicitly use delimiters or instructions to ignore embedded commands within the transcript text.
- Capability inventory: The skill utilizes file system creation (mkdir), file writes, and the execution of subagents via the Task tool.
- Sanitization: No sanitization or filtering of the transcript data is performed before it is analyzed.
- [COMMAND_EXECUTION]: The skill performs local file system management including creating specific directory structures for intermediate files and recommends the use of command-line tools like markitdown for document conversion.
Audit Metadata