famou-result-visualization

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from the user and processes it into an output format.
  • Ingestion points: The skill reads 'Problem Description' and 'Python code' provided by the user (as described in SKILL.md).
  • Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions within the ingested data.
  • Capability inventory: The skill has the capability to write a local HTML file (famou_viz_result.html).
  • Sanitization: There are no explicit instructions for sanitizing or escaping content extracted from the Python code before it is interpolated into the HTML template, which could lead to Cross-Site Scripting (XSS) if the user provides malicious input.
  • [EXTERNAL_DOWNLOADS]: The skill generates HTML that relies on external resources from well-known services.
  • Evidence: The template in SKILL.md references React, Babel, and Tailwind CSS via Cloudflare's CDN (cdnjs.cloudflare.com) and Tailwind's CDN (cdn.tailwindcss.com), as well as Google Fonts. These are established, well-known services used for UI rendering.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 05:39 AM