article-magazine
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill's example HTML file references Tailwind CSS from cdn.tailwindcss.com and typography resources from Google Fonts (fonts.googleapis.com and fonts.gstatic.com). These are well-known and standard services used for web layout and styling.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and transform user-provided markdown or notes into a specific HTML layout, which creates a surface for indirect prompt injection.\n
- Ingestion points: User-supplied markdown content as defined in the SKILL.md instructions.\n
- Boundary markers: The template does not specify clear delimiters or boundary markers to isolate user input from the formatting instructions.\n
- Capability inventory: The skill consists purely of formatting instructions and HTML/CSS templates; no executable scripts, subprocess calls, or network-writing capabilities are present within the skill files.\n
- Sanitization: There is no evidence of sanitization or input validation to prevent the inclusion of malicious instructions within the transformed data.
Audit Metadata