grapesjs

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill defines an attack surface for indirect prompt injection.\n- Ingestion points: The GrapesJS editor processes untrusted content through methods such as editor.addComponents(html) (api-reference.md) and editor.loadProjectData(json) (storage-reference.md).\n- Boundary markers: No explicit delimiters or instructions to ignore natural language prompts embedded in HTML/JSON data are defined in the provided documentation.\n- Capability inventory: The skill utilizes the GrapesJS StorageManager, which can perform network requests (GET, POST, PATCH) to remote endpoints (storage-reference.md). The editor also handles script components that execute JavaScript within the canvas.\n- Sanitization: While GrapesJS parses input into a model, the skill documentation lacks specific sanitization layers intended to prevent natural language instructions from influencing AI agent behavior.\n- [EXTERNAL_DOWNLOADS]: The documentation references the installation and usage of 'grapesjs-mjml' and 'mjml-browser', which are well-known and legitimate packages in the GrapesJS ecosystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 05:18 PM