shape
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill contains an attack surface where untrusted data could influence the agent's behavior or file output content.
- Ingestion points: Processes user-supplied design briefs via the
$ARGUMENTSvariable inSKILL.md. - Boundary markers: Absent; there are no explicit delimiters or protective instructions defining the boundary of the external UI brief.
- Capability inventory: Possesses file-writing capability, specifically the option to create or append structured UI definitions to
.ui-craft/spec.md. - Sanitization: Absent; the skill does not detail any sanitization, escaping, or strict schema enforcement on the user input before processing or saving.
Audit Metadata