design-systems
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, which could potentially contain hidden instructions designed to influence the agent's behavior during code generation or system analysis.
- Ingestion points: The skill is instructed to inventory component data, consumption patterns, and design tokens from the local project environment and the Figma Variables API, as described in
SKILL.mdandreferences/guide.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when the agent incorporates retrieved external data into its responses or generated code.
- Capability inventory: The agent performs code generation (TypeScript, Swift, Kotlin), creates automated migration scripts (codemods), and produces decision records, providing a surface where malicious input could influence generated logic or documentation.
- Sanitization: The skill lacks explicit requirements for the agent to sanitize, validate, or escape content retrieved from external sources before including it in its output.
Audit Metadata