clean-code-guard
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or remote code execution risks were identified. The skill consists of markdown-based instructions and reference materials that promote industry-standard best practices in software engineering and AI-specific safety guardrails.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to ingest and analyze untrusted code provided by users, which constitutes a vulnerability surface for indirect prompt injection. However, the instructions provided (especially those regarding validation at trust boundaries) serve to reinforce agent scrutiny rather than weaken it.
- Ingestion points: Target files and code diffs provided for review, audit, or refactoring in
SKILL.md. - Boundary markers: Absent; the skill does not explicitly instruct the agent to use unique delimiters to isolate the code being analyzed from its core instructions.
- Capability inventory: The skill is a portable instruction set that uses the agent's existing file-reading and analysis capabilities without requiring external tools, scripts, or network access.
- Sanitization: Absent; the skill relies on the agent's internal safety filters and the rigorous review imperatives defined in the reference files.
Audit Metadata