design-critique
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill is designed to ingest and analyze external data, including Figma URLs and file references, which could contain untrusted instructions.
- Ingestion points: Untrusted data enters the agent context through the
$ARGUMENTSparameter and referenced Figma URLs inSKILL.md. - Boundary markers: The prompt lacks explicit delimiters or instructions to the agent to ignore potentially malicious text embedded within the designs being reviewed.
- Capability inventory: The skill utilizes connectors to inspect Figma components, layers, and design tokens, and can cross-reference with user feedback logs.
- Sanitization: No explicit sanitization or validation of the content retrieved from external design files is defined within the skill instructions.
Audit Metadata