skill-style-css-clean
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides comprehensive documentation and guidelines for CSS auditing. Analysis of all instructions and reference files confirms they are focused solely on development best practices without any malicious intent.
- [SAFE]: No hidden or obfuscated code, remote scripts, or unauthorized network operations were identified. References to external resources target well-known and trusted services.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external CSS/SCSS files, which represents an indirect prompt injection surface. However, this behavior is essential to its primary function as an auditor. The skill does not possess capabilities for code execution, file writing, or network exfiltration that would allow an attacker to exploit this surface.
- Ingestion points: Protocol Step 1 and 2 in
SKILL.mdinstruct the agent to list and read all project CSS/SCSS files. - Boundary markers: No explicit markers or 'ignore instructions' warnings are defined for the audited content.
- Capability inventory: No dangerous tools or commands (exec, eval, network, file-write) are invoked by the skill.
- Sanitization: External content is processed as raw text for analysis.
Audit Metadata