finishing-a-development-branch
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to run test suites and perform Git operations such as merging, pushing, and deleting branches. This is part of the intended primary purpose of the skill.
- [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill reads branch names and commit lists from the local environment (SKILL.md).
- Boundary markers: The workflow is constrained by presenting four specific, structured options to the user, reducing the risk of autonomous deviations.
- Capability inventory: The skill has capabilities to execute local test commands, modify the repository state via Git, and remove worktrees.
- Sanitization: The skill uses quoted heredoc delimiters (EOF) when creating Pull Request descriptions, which helps prevent unintended shell expansion or injection during command construction.
Audit Metadata