design-critique
Pass
Audited by Gen Agent Trust Hub on Nov 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze untrusted external content, which is a potential surface for indirect prompt injection attacks.
- Ingestion points: Accepts Figma URLs, file references, and user-provided screenshots/descriptions via the
$ARGUMENTSparameter inSKILL.md. - Boundary markers: No explicit delimiter or instruction-ignoring markers are defined for the design content being analyzed.
- Capability inventory: The skill performs read operations and analysis; it does not possess capabilities for file writing, code execution, or network exfiltration outside of standard platform connectors.
- Sanitization: No specific sanitization or validation of the external content is implemented in the skill instructions.
Audit Metadata