create-html-report

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill utilizes a local Python renderer (render_report.py) that operates entirely within the sandbox using standard libraries, avoiding risks associated with unverifiable remote dependencies.
  • [SAFE]: The system implements a 'Self-contained' contract, ensuring that reports do not depend on external CDNs, fonts, or scripts, which effectively prevents data exfiltration and tracking.
  • [SAFE]: All untrusted data processed by the skill is escaped using Python's html.escape before being embedded in HTML or SVG outputs, significantly reducing the risk of indirect injection and cross-site scripting (XSS).
  • [SAFE]: The mandatory validation process (validate_report.py) checks for security violations such as inline event handlers, javascript: URLs, and external resource references, failing the task if any security threshold is not met.
  • [SAFE]: Documentation explicitly instructs the agent to redact sensitive information like API keys and tokens found in input data, demonstrating a strong security posture regarding data privacy.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 12:07 AM
Security Audit — agent-trust-hub — create-html-report