finishing-a-development-branch
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to run local test suites using npm, cargo, pytest, or go. It also performs standard branch management through git commands.- [EXTERNAL_DOWNLOADS]: The skill triggers network operations via git pull, git push, and the GitHub CLI (gh) to interact with remote repositories and manage Pull Requests.- [PROMPT_INJECTION]: There is an indirect injection surface where the agent ingests data from branch names, commit logs, and test results to populate a Pull Request template.
- Ingestion points: Data is pulled from git branch metadata and command-line outputs of test tools.
- Boundary markers: There are no explicit delimiters to isolate ingested data from agent instructions.
- Capability inventory: The agent has the ability to execute shell commands and modify remote repository state.
- Sanitization: No explicit sanitization or validation of the branch names or commit messages is performed before they are included in the PR body.
Audit Metadata