number-details

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEOBFUSCATIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [OBFUSCATION]: The demo/index.html file contains a large Base64-encoded string used to store the demo's HTML and CSS content. This is a common bundling technique and the decoded content was found to be benign, consisting of standard web code and references to well-known font services.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an inherent risk of indirect prompt injection as it processes user-provided briefs to generate HTML and JavaScript.
  • Ingestion points: User prompts and product briefs in demo/PROMPT.md.
  • Boundary markers: Absent.
  • Capability inventory: Generation of HTML/JS files that include external library dependencies.
  • Sanitization: Relies on the agent's default safety mechanisms.
  • [EXTERNAL_DOWNLOADS]: Metadata in demo/source.json references external assets and libraries from well-known and trusted sources, such as Google Fonts, Cloudflare, and Unsplash. These references are part of the demo's design and do not represent a security risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 01:31 AM
Security Audit — agent-trust-hub — number-details