grapesjs-studio-sdk
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements an AI Chat integration that processes project context and user-supplied messages.
- Ingestion points:
ChatRequestBodycontaining messages and project context inrules/plugins/ai/ai-backend.md. - Boundary markers: Present; the implementation supports system prompt customization with preambles and postambles to define AI behavior in
rules/plugins/ai/ai-backend.md. - Capability inventory: The AI agent can execute tools (e.g.,
getWeather,generateImage) and trigger editor commands likecore:previewas shown inrules/plugins/ai/ai-backend.mdandrules/plugins/ai/ai-chat.md. - Sanitization: Implicitly handled by the underlying Vercel AI SDK; no explicit sanitization logic is detailed in the skill scripts.
- [EXTERNAL_DOWNLOADS]: Fetches configurations, media assets, and fonts from well-known services.
- Fetches placeholder images from
picsum.photosandplacehold.co. - Loads font files from
fonts.gstatic.cominrules/configuration/fonts.md. - References widely used libraries (jQuery, Bootstrap, reset-css) from established CDNs including
cdnjs.cloudflare.comandcdn.jsdelivr.net. - [REMOTE_CODE_EXECUTION]: The skill configuration allows for the dynamic loading of scripts from
cdn.jsdelivr.netto support third-party plugin functionality. - Example:
cdnScriptoptions inrules/plugins/components/fslightbox.md,rules/plugins/components/lightGallery.md,rules/plugins/components/swiper.md, andrules/plugins/rte/tinymce.mdpoint to official versions of FsLightbox, lightGallery, Swiper, and TinyMCE.
Audit Metadata