finishing-a-development-branch
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill guides the agent to execute standard development commands such as
npm test,cargo test,pytest, and variousgitcommands (checkout, pull, merge, branch, push, worktree) to manage the development lifecycle. - [EXTERNAL_DOWNLOADS]: The skill interacts with remote repositories through
git pushandgh pr create, which are standard operations for synchronizing code with platforms like GitHub. - [PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection as it processes data from external command outputs.
- Ingestion points: Command outputs from
npm test,cargo test,pytest,go test,git merge-base, andgit worktree listare read into the agent's context. - Boundary markers: No specific delimiters or instructions are used to separate command outputs from the agent's instructions.
- Capability inventory: The skill allows the execution of
git,gh, and language-specific test runners. - Sanitization: No filtering or validation is performed on command results before processing.
Audit Metadata