Finishing a Development Branch
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- COMMAND_EXECUTION (LOW): The skill executes local shell commands for git, gh (GitHub CLI), and language-specific test runners (npm, pytest, cargo, go). These are standard development operations but constitute a command execution surface.
- Indirect Prompt Injection (LOW): The skill processes untrusted metadata from the repository environment and interpolates it into shell commands without explicit sanitization or escaping. Ingestion points:
SKILL.mdrelies on output fromgit branch --show-currentandgit worktree list. Boundary markers: Absent for shell variable interpolation. Capability inventory: Subprocess execution ofgit,gh, and project test suites. Sanitization: None specified; the skill relies on the agent's default shell handling for variables like<feature-branch>and<worktree-path>into command strings.
Audit Metadata