vault-scribe
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted source material (transcripts, meeting notes) which presents an indirect prompt injection surface.
- Ingestion points: External text material enters the agent context through the analysis workflow described in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or isolation rules to prevent instructions within the source material from being executed by the agent.
- Capability inventory: The skill utilizes Read, Grep, Edit, and Write tools (defined in SKILL.md) which allow the agent to modify files on the local filesystem.
- Sanitization: There are no verification or sanitization steps mentioned for processing the input material before it is used to generate or edit notes.
- [NO_CODE]: The skill consists exclusively of markdown documentation and reference files; it contains no executable scripts, binaries, or automated code triggers.
Audit Metadata