finishing-a-development-branch

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses several shell commands to manage the Git workflow, including git, gh (GitHub CLI), and common test runners (pnpm, pytest, cargo, go). These operations are essential to the skill's primary function of branch management and do not involve unauthorized access or external exfiltration.
  • [COMMAND_EXECUTION]: The skill includes functionality to delete branches and remove Git worktrees. These are gated behind specific user choices and, in the case of the 'discard' option, require explicit textual confirmation from the user to prevent accidental data loss.
  • [PROMPT_INJECTION]: The skill provides structured templates and strict instructions for the agent's interaction style, which helps maintain predictable behavior and reduces the surface area for unexpected instruction overrides.
  • [DATA_EXFILTRATION]: No patterns of data exfiltration were detected. Network operations are limited to standard version control actions (git push, git pull, gh pr create) directed at the project's own repository (origin).
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 07:12 AM
Security Audit — agent-trust-hub — finishing-a-development-branch