penpot-component-factory
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected across the skill files and scripts.
- [COMMAND_EXECUTION]: The skill uses the 'execute_code' tool to run JavaScript snippets that interact with the Penpot environment. This execution is limited to the Penpot plugin API (e.g., 'penpot.createBoard', 'penpot.library.local.createComponent') and is the primary intended functionality of the skill for UI automation.
- [DATA_EXFILTRATION]: No network operations ('curl', 'fetch', etc.) or access to sensitive local files (credentials, SSH keys) were found. The skill operates entirely within the context of the Penpot application data.
- [PROMPT_INJECTION]: The instructions follow standard operational guidelines for a design-system agent. There are no attempts to bypass safety filters, ignore prior instructions, or extract system prompts.
- [REMOTE_CODE_EXECUTION]: The skill does not download or execute code from external sources. All logic is contained within the provided local script files.
- [SAFE_PRACTICE]: The documentation (specifically 'references/03-variant-api.md' and 'scripts/createVariantGroup.js') proactively warns the user about platform-specific risks, such as potential file corruption due to known backend API limitations, and provides safe fallback procedures.
Audit Metadata