companify-chro

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates entirely on local project documentation (company/people.md, company/strategy.md, etc.) and does not perform any network requests or external data transfers.
  • [SAFE]: Instructions focus on organizational structuring and do not include any shell command execution, dynamic code loading, or privilege escalation patterns.
  • [SAFE]: The skill does not access sensitive system paths or credentials; it specifically targets business-related markdown files within the project directory.
  • [PROMPT_INJECTION]: No prompt injection or behavior override patterns were detected. The instructions maintain a clear professional role without attempting to bypass safety guardrails.
  • [DATA_EXPOSURE]: The skill documents human supervision requirements for AI agents (legal, financial, ethical), which promotes safety and accountability in agent-based workflows.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 10:25 PM
Security Audit — agent-trust-hub — companify-chro