finishing-a-development-branch
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill performs various terminal commands using standard development tools such as Git, GitHub CLI (gh), npm, cargo, and pytest. These actions are necessary for the skill's stated purpose of managing branch integration and cleanup.
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests implementation details to generate Pull Request descriptions.
- Ingestion points: The agent ingests information about the completed implementation to populate the Pull Request summary (SKILL.md).
- Boundary markers: The skill uses single-quoted heredocs ('EOF') when creating Pull Request bodies, which is a security best practice to prevent shell variable expansion or command injection during the string interpolation process.
- Capability inventory: The skill possesses the capability to execute shell commands, perform file system operations via git, and interact with remote repositories through the GitHub CLI.
- Sanitization: The instructions guide the agent to structure the output into specific bullet points, reducing the risk of accidental obedience to instructions embedded within the code changes.
Audit Metadata