finishing-a-development-branch
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements standard developer workflows for branch integration and cleanup. It does not exhibit malicious patterns, obfuscation, or unauthorized data access. The logic emphasizes safety through test verification and user confirmation for deletions.
- [COMMAND_EXECUTION]: The skill utilizes standard command-line tools (git, gh, npm, cargo, pytest, go) strictly for Git operations and running local project tests as part of the development lifecycle.
- [INDIRECT_PROMPT_INJECTION]: The skill interacts with external data sources such as branch names and test outputs which serves as the ingestion point. It mitigates potential risks by using boundary markers like the 'EOF' quoted heredoc in PR creation and limiting agent capabilities to four specific, predefined workflow options. Sanitization is further enforced by requiring exact string matches for confirmation of destructive commands.
Audit Metadata