apply-design-system
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Figma (layer names, text content, and metadata) which could be used to deliver hidden instructions to the agent.
- Ingestion points: Figma node names, properties, and metadata retrieved through tools mentioned in
SKILL.md. - Boundary markers: Absent; there are no explicit delimiters or instructions to ignore instructions embedded in the design data.
- Capability inventory: The skill uses the
use_figmatool to perform design mutations, creating a pathway for potential exploits if malicious data is processed. - Sanitization: The skill does not describe any validation or sanitization of external design content before it is processed by the agent.
Audit Metadata