meeting-memo-creation
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted content from meeting transcripts and repository files such as contacts.md and previous memos. This creates an indirect prompt injection surface where instructions hidden in the data could influence the agent's output.
- Ingestion points: User-provided meeting transcripts, recordings, and repository files including contacts.md, memo-template.md, and previous memos.
- Boundary markers: No delimiters or instructions to ignore embedded commands are present in the asset resolution or processing logic.
- Capability inventory: The skill uses file searching and reading tools to gather context and generates markdown documentation. It does not have access to network or shell execution tools.
- Sanitization: The skill does not implement validation or sanitization of the content extracted from external or repository sources.
Audit Metadata