hedge-fund-manager
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The analyzed skill is entirely comprised of instructional markdown defining agent delegation and report generation logic. No executable scripts, binaries, or configuration files are present in the provided content.
- [SAFE]: The skill instructions enforce critical safety boundaries, specifically a 'notification-first' policy that explicitly forbids the agent from placing trades automatically, ensuring a human must review and execute any financial actions.
- [SAFE]: No data exfiltration patterns, external network requests, or sensitive file access were detected. The skill operates within its own defined fund state and references local sub-skills.
- [SAFE]: The 'audit log' functionality is described as a security and transparency feature (logging to a .jsonl file) rather than a malicious persistence mechanism.
Audit Metadata