vault-search
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The vault-search skill provides a legitimate interface for an AI agent to query past architectural decisions, bug fixes, and implementation patterns using the
vault-clitool. The instructions include sound engineering principles such as proactive searching before implementation and strict anti-hallucination protocols when no results are found. No evidence of prompt injection, unauthorized data access, or remote code execution was found across the skill files.
Audit Metadata