figma-console-mcp-skills
Fail
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's installation instructions require cloning a repository from 'github.com/PercentProduction/figma-console-mcp-skills-347.git'. This vendor and repository are not recognized as trusted or well-known services, posing a risk of downloading unverified code.
- [REMOTE_CODE_EXECUTION]: Following the repository clone, the skill directs the user to execute 'npm install' and 'npm start'. Running installation scripts and start commands from an untrusted external repository allows for arbitrary code execution on the user's local environment.
- [INDIRECT_PROMPT_INJECTION]: The skill processes and traverses complex Figma node structures, including variable names and component descriptions which are often controlled by external collaborators. This creates an attack surface where malicious instructions embedded in design files could influence the agent's behavior during automated audits or documentation generation.
Recommendations
- AI detected serious security threats
Audit Metadata