ui-designer
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's workflow involves reading and processing external UI language, constraints, and user-flow context. This ingestion of potentially untrusted data creates a surface for indirect prompt injection. However, the skill lacks any high-risk capabilities such as command execution, file-writing, or network operations, and the metadata specifies a read-only sandbox mode.
- Ingestion points: Processes existing UI language and context context (SKILL.md).
- Boundary markers: None explicitly defined.
- Capability inventory: No subprocess calls, network ops, or file system modifications detected.
- Sanitization: None detected.
- [SAFE]: The skill is composed entirely of natural language instructions and configuration metadata. No malicious patterns, obfuscation, or remote code dependencies were identified.
Audit Metadata