atomic-commits

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes various git commands including status, diff, and log to inspect the working tree and repository history for classification purposes.
  • [COMMAND_EXECUTION]: Utilizes specialized tools cortex git commit and cortex git patch for staging and committing changes. These are recognized as legitimate vendor-owned resources from 'NickCrew' and are central to the skill's intended functionality.
  • [SAFE]: Includes explicit safety instructions to prevent data loss, specifically cautioning against destructive commands such as git reset --hard, git checkout --, and git stash drop.
  • [SAFE]: Implements a human-in-the-loop checkpoint by instructing the agent to consult the user before committing files not authored by the agent or when the repository state is confusing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 04:46 PM
Security Audit — agent-trust-hub — atomic-commits