html-visual

Pass

Audited by Gen Agent Trust Hub on Feb 25, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from local files without explicit sanitization or boundary markers.
  • Ingestion points: Processes file paths provided in arguments or automatically identified project files.
  • Boundary markers: Absent; the skill does not use delimiters to isolate external file content.
  • Capability inventory: The skill can read local files, write HTML files, and recommend that the user open the generated content.
  • Sanitization: Input content is analyzed for visualization without filtering for potentially malicious embedded instructions.
  • [EXTERNAL_DOWNLOADS]: The skill references several external JavaScript libraries to enable its visualization functionality.
  • Resources: Fetches D3.js, Mermaid, Chart.js, Reveal.js, and Tailwind CSS from reputable CDNs like d3js.org and jsdelivr.net. These are well-known technology services and are considered safe sources in this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 25, 2026, 11:39 AM