ui-design
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external design assets and project code, creating an attack surface for indirect prompt injection attacks.\n
- Ingestion points: The agent is instructed to ingest user-provided Figma files, screenshots, UI specifications, and project code as primary sources of design authority and context (SKILL.md, Sections 1 and 2).\n
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to separate untrusted user input from system prompts, which may allow instructions embedded in metadata or design assets to influence agent behavior (SKILL.md).\n
- Capability inventory: The agent has the authority to modify project source code and UI components (SKILL.md, Section 12) and verify these changes using rendering and browser-based verification tools (SKILL.md, Section 13).\n
- Sanitization: The instructions do not include requirements for sanitizing or validating the content of ingested assets before they are used to guide code generation or layout decisions (SKILL.md).
Audit Metadata