finishing-a-development-branch
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes standard development and version control commands, including
git(branch management, worktree removal), and test runners such asnpm test,cargo test,pytest, andgo test. These operations are fundamental to the skill's purpose as a development workflow tool. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local development environment, creating a potential surface for indirect prompt injection.
- Ingestion points: The skill reads file names through
git status --porcelainand branch names throughgit branchandgit rev-parse. - Boundary markers: No specific delimiters are used to wrap the output of git commands to prevent the agent from interpreting file names as instructions.
- Capability inventory: The skill has the capability to delete branches (
git branch -d/-D) and remove directory structures (git worktree remove). - Sanitization: The skill includes a critical safety check requiring the user to provide the exact confirmation string
discardbefore any destructive deletion is performed, which significantly mitigates the risk of accidental or malicious automated execution.
Audit Metadata