consult
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates entirely as a reasoning and persona-simulation layer using local markdown profiles. No malicious instructions or bypass attempts were found.
- [SAFE]: There are no external network operations, remote script downloads, or third-party package dependencies.
- [SAFE]: File system access is restricted to reading provided profiles and a local configuration file (~/.claude/counsel-blocklist.json) used to manage expert visibility. No access to sensitive system credentials or private keys was detected.
- [SAFE]: The skill defines clear boundaries, explicitly stating it does not execute code, implement changes, or make decisions, mitigating potential impact from indirect prompt injection.
Audit Metadata