pm-roadmap-update

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a strong safety protocol for handling external data. It explicitly instructs the agent to treat roadmap content, PRDs, and stories as untrusted data and forbids following any instruction-like text found within them.
  • [SAFE]: Data protection is enforced through mandatory exclusion of sensitive file patterns such as .env, **/secrets/**, **/.ssh/**, and cryptographic keys during codebase scans.
  • [SAFE]: The skill uses a two-phase workflow (Analysis vs. Update) with a mandatory 'HARD STOP' for human review and approval before any file modifications are applied.
  • [SAFE]: Tool usage is constrained to a specific set of allowed operations. Network usage is limited to standard Git operations for retrieving remote URLs and committing local changes.
  • [SAFE]: A pre-execution hook (validate-roadmap.sh) is configured to ensure data integrity during write operations, providing an automated layer of validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 09:29 AM
Security Audit — agent-trust-hub — pm-roadmap-update