cmd-pr-sculpt-code
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use standard CLI tools including
git,gh(GitHub CLI),grep,sed,xargs, andcutto determine the base branch and analyze file differences. These operations are essential for the skill's purpose of refactoring code and are performed on the local repository state. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) due to its core functionality.
- Ingestion points: The agent is instructed to read all changed files in full from the codebase (SKILL.md).
- Boundary markers: No explicit delimiters or instructions are provided to help the agent distinguish between the code it is 'sculpting' and the instructions it should follow.
- Capability inventory: The skill allows for repository exploration (git/gh) and direct file modification ('Apply fixes directly').
- Sanitization: There is no evidence of sanitization for the codebase content before processing.
- While this is a vulnerability surface, it is considered safe in this context as it is the intended primary purpose of the skill and does not involve automated execution of untrusted code or network exfiltration.
Audit Metadata