ai-component-description
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection due to its core function of ingesting and summarizing external data.
- Ingestion points: The skill reads component information from external sources including Figma nodes, Storybook metadata, and TypeScript source files (Step 0).
- Boundary markers: There are no specific instructions or delimiters defined to separate the ingested external content from the agent's internal reasoning or output generation.
- Capability inventory: The skill is capable of writing the generated descriptions back to Figma component nodes using MCP tools such as
figma_set_descriptionoruse_figma(Step 5). - Sanitization: The instructions do not mandate the sanitization or escaping of external data before it is processed or written back to the Figma platform.
Audit Metadata