figma-mcp
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation recommends the installation of the
figma-developer-mcp(rebranded as Framelink MCP) package from the npm registry. This is a well-known community tool used to interface with the Figma API via the Model Context Protocol.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process structured design data from external Figma URLs, creating a surface for potential indirect prompt injection.\n - Ingestion points: Design data (hierarchy, styles, and variables) enters the agent context via the
get_figma_dataandget_figma_variablestools as defined in the workflow inSKILL.md.\n - Boundary markers: Absent; the instructions do not include specific delimiters or warnings to ignore instructions that might be embedded within design text nodes.\n
- Capability inventory: The skill generates semantic HTML, CSS, and React components based on the ingested data as described in
SKILL.md.\n - Sanitization: No explicit sanitization or validation of the external design content is mentioned in the skill's instructions.
Audit Metadata