project-manager-bootstrap

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns detected. The skill provides clear instructions for an AI agent to operate in a 'Project Manager' mode, emphasizing documentation (DECISIONS.md, ASSUMPTIONS.md) and progress reporting.
  • [COMMAND_EXECUTION]: The skill encourages agent autonomy ('You can autonomously judge the next step, no need to wait for my confirmation'), which involves the use of shell or file system tools. This is the intended primary purpose of the skill for prototyping and is accompanied by suggested 'stop lines' and 'review gates' to maintain control.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 07:52 AM
Security Audit — agent-trust-hub — project-manager-bootstrap