figma-mcp-integration
Warn
Audited by Socket on May 18, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill’s Figma-read/write scope matches its stated purpose, but its trust model is weak. It relies on download-and-execute patterns and executes a third-party MCP server from an unrelated publisher via mutable install paths, creating meaningful supply-chain and design-data exposure risk without clear same-org provenance.
Confidence: 84%Severity: 74%
Audit Metadata