justhold-mdx-content
Pass
Audited by Gen Agent Trust Hub on Jul 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines legitimate architectural patterns for managing MDX blog content via a CMS. It references standard project files and well-known services like Supabase and Cloudflare R2 for data management.
- [PROMPT_INJECTION]: Evaluation of indirect prompt injection surfaces identifies that the skill handles external MDX content from Cloudflare R2. This is consistent with its primary purpose as a content management tool.
- Ingestion points: MDX bodies are loaded from Cloudflare R2 storage paths (e.g., posts///content.mdx).
- Boundary markers: No specific delimiters or "ignore" instructions are provided for processed content.
- Capability inventory: The skill is used for editing posts, MDX components, and managing R2 keys.
- Sanitization: No explicit sanitization or validation steps are outlined in the instructions for the external content.
Audit Metadata