finishing-a-development-branch
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard development tools including Git, the GitHub CLI, and common test runners like npm, cargo, and pytest. These commands are executed locally to manage the development branch lifecycle and are appropriate for the skill's intended use.
- [SAFE]: The design incorporates critical safety guardrails, such as preventing any merge actions if test suites fail and requiring a specific typed confirmation ('discard') before permanently deleting branches or worktrees. It also uses quoted heredocs ('EOF') to safely handle multi-line PR descriptions.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection via data ingested from the local environment (e.g., branch names or commit messages). 1. Ingestion points: Local environment data via git commands in SKILL.md. 2. Boundary markers: Employs heredoc (EOF) delimiters when generating Pull Requests. 3. Capability inventory: Capabilities are limited to subprocess execution of standard CLI tools. 4. Sanitization: Relies on standard shell argument construction without additional explicit filtering.
Audit Metadata