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 uses standard git and GitHub CLI commands to manage local and remote branches. These operations are appropriate for the tool's primary purpose.
- Indirect Prompt Injection (SAFE): 1. Ingestion points: Git branch names and commit metadata are read from the local repository. 2. Boundary markers: Quoted shell heredocs (cat <<'EOF') are used to prevent unintended command execution in PR bodies. 3. Capability inventory: Subprocess calls to git, gh, and common test runners. 4. Sanitization: Relies on robust shell quoting patterns for variable interpolation.
- Data Exposure (SAFE): No access to sensitive credentials, SSH keys, or environment secrets was detected. GitHub operations are conducted via the standard CLI.
- Privilege Escalation (SAFE): All commands run with the agent's current user permissions; no administrative escalation (e.g., sudo) is present.
Audit Metadata