Penpot Uiux Design

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the official Penpot MCP server from the repository at github.com/penpot/penpot-mcp.git.
  • [COMMAND_EXECUTION]: The setup instructions guide the user to execute shell commands including git clone, npm install, and npm run bootstrap to prepare the local environment.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface (Category 8).
  • Ingestion points: The skill reads shape structures, text content, and component hierarchies from active Penpot design files using the mcp__penpot__execute_code tool.
  • Boundary markers: No specific delimiters or instructions to ignore instructions embedded in the design data are present.
  • Capability inventory: The skill has high capabilities within the Penpot environment, including creating, modifying, or deleting boards and shapes via arbitrary JavaScript execution.
  • Sanitization: There is no evidence of sanitization or validation of the data retrieved from the design file before it is interpreted by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 07:21 PM