finishing-a-development-branch

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill executes standard developer commands (git, npm, cargo, pytest, go) which are necessary for testing and version control automation.
  • [DATA_EXFILTRATION] (SAFE): It interacts with GitHub via the gh CLI to push code and create Pull Requests. This activity is restricted to a trusted domain and aligns with the skill's primary purpose.
  • [PROMPT_INJECTION] (LOW): The skill has a surface for indirect prompt injection. 1. Ingestion points: Branch names and PR metadata are used in commands. 2. Boundary markers: The skill uses EOF heredocs for PR bodies to provide some separation. 3. Capability inventory: The skill can execute local tests, manage Git branches, and create PRs. 4. Sanitization: No explicit sanitization is performed on user-controlled strings like branch names or commit messages.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:50 PM