finishing-a-development-branch
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements standard, high-quality development workflows, emphasizing test success and environment awareness before merging or deleting branches.
- [COMMAND_EXECUTION]: Shell commands are used appropriately for Git state detection (
git rev-parse) and workspace management (git worktree). The skill does not perform any network operations to unknown domains or execute arbitrary remote scripts. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local command outputs, such as test failures and Git status. While this is a theoretical vector for prompt injection from a malicious repository, the risk is effectively mitigated by the skill's strict menu-driven logic and the requirement for explicit human input (e.g., typing 'discard') for destructive operations.
Audit Metadata