harness-audit
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates under a non-mutating, read-only discipline, using standard CLI tools (grep, find, wc) to inventory repository artifacts without modifying the audited codebase.
- [SAFE]: It contains a dedicated security enforcement step in 'references/report-format-enforcer.md' that scans for and redacts sensitive data, such as AWS keys, private keys, and bearer tokens, before the report is exported.
- [SAFE]: All external links and references target the vendor's official GitHub organization (somnio-software), which is consistent with the skill's authorship and legitimate purpose.
- [SAFE]: The multi-agent workflow (orchestrator, analyzer, report-writer) provides a structured processing pipeline that reduces the risk of malicious instructions in the audited data influencing the agent's core behavior.
Audit Metadata