commit
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: Analysis of the skill instructions and metadata shows no malicious patterns. The skill focuses on standardizing development workflows and ensuring compliance with engineering practices.\n- [COMMAND_EXECUTION]: The skill instructs the agent to run
git branch --show-currentas a safety check to identify the current branch environment. This is a standard, non-destructive read-only operation used to prevent errors.\n- [PROMPT_INJECTION]: The skill contains strong directives (e.g., "ALWAYS use this skill", "MUST create a feature branch") intended to enforce organizational commit policies. These instructions are functionally relevant to the skill's purpose and do not attempt to bypass the agent's core safety filters or extract system instructions.
Audit Metadata