ui-skills
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a development style guide and does not perform network operations, file system modifications, or sensitive command execution. All referenced external libraries (e.g., Tailwind CSS, Radix, motion/react) are well-known industry standards.
- [PROMPT_INJECTION]: The skill includes an instruction to review user-provided files via the
/ui-skills <file>command, which is an ingestion point for untrusted data. - Ingestion points: Files provided by the user for architectural review in
SKILL.md. - Boundary markers: None present; the agent is not explicitly told to ignore instructions embedded in the analyzed code.
- Capability inventory: Zero; the skill lacks any access to dangerous tools such as subprocess execution, network requests, or file-writing tools across the instructions.
- Sanitization: None; the content is reviewed as plain text code samples.
Audit Metadata