Finishing a Development Branch
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute various shell commands including test runners (npm, cargo, pytest, go), git operations (merge, checkout, push, worktree), and the GitHub CLI (gh pr create).
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface where untrusted or environment-derived data is interpolated into shell commands without explicit sanitization.
- Ingestion points: Data enters the process via user-provided Pull Request titles and environment-derived branch names retrieved via
git branch --show-current. - Boundary markers: No explicit boundary markers or instructions to escape special characters are provided for the interpolated variables such as
<feature-branch>,<base-branch>, or<title>. - Capability inventory: The skill has the capability to execute shell commands with broad reach, including git branch deletion (
git branch -D), remote push (git push), and directory removal (git worktree remove). - Sanitization: There is no evidence of sanitization or validation for the inputs before they are executed in the shell context, which could potentially lead to command injection if a branch name or title contains shell metacharacters.
Audit Metadata