skills/hurtzdonut559/software-development-superpowers/finishing-a-development-branch/Gen Agent Trust Hub
finishing-a-development-branch
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates standard development operations by instructing the agent to execute tools like
git,npm test,pytest, andcargo test. These commands are essential to the skill's primary function of branch management and code verification. The instructions include safety logic, such as ensuring tests pass before merging and requiring a specific working directory change before removing worktrees. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the local environment, including test suite output and git branch names. While this represents a theoretical indirect prompt injection surface, the risk is mitigated by the skill's implementation of a fixed, structured menu of options and the requirement for explicit, typed user confirmation ("discard") before performing destructive operations.
Audit Metadata