clean-code
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze untrusted data in the form of user-provided code snippets for reviews, refactoring, and quality assessments (as described in the triggers for "code review" and "pull requests" in SKILL.md).
- Ingestion points: The skill triggers on and processes user-provided code, PR diffs, and refactoring requests.
- Boundary markers: The instructions do not specify the use of boundary markers or delimiters to isolate user-provided code from the agent's internal instruction context.
- Capability inventory: While the skill consists only of markdown files and no executable scripts, the agent using this skill typically operates in environments with file system access and shell capabilities, which could be targeted by instructions embedded in analyzed code.
- Sanitization: No specific sanitization, escaping, or filtering instructions are provided for handling the external content before processing.
Audit Metadata