ui-skills
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and metadata. It does not include any executable scripts, binary files, or automated tool configurations.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze user-provided interface code and external design guides, creating an ingestion surface for untrusted data. However, the skill lacks tool permissions or executable capabilities (such as file writes or network exfiltration) that would allow for an impactful attack.
- Ingestion points: User-provided interface code, design systems, and external guides mentioned in the Procedure section of SKILL.md.
- Boundary markers: None specified in the instructions to delimit external content.
- Capability inventory: No subprocess calls, network operations, or file system modifications are present in the skill.
- Sanitization: No sanitization or validation logic is defined for the input data.
- [EXTERNAL_DOWNLOADS]: The skill contains a reference link to a public GitHub repository for supplemental UI guidance. This targets a well-known service for documentation purposes and does not involve the automated execution of remote code.
Audit Metadata