tables

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies and processes HTML table structures within project files to apply accessibility rules.
  • Ingestion points: HTML files containing <table> elements within the project context (as specified in SKILL.md).
  • Boundary markers: None explicitly defined for the input data, although the skill enforces a strict structural schema for output.
  • Capability inventory: The skill's instructions are limited to generating, modifying, or reviewing HTML and CSS markup. No subprocess execution, file-write, or network-write capabilities are present in the skill scripts.
  • Sanitization: Not present; the skill treats table content as data to be reorganized rather than instructions to be executed.
  • [EXTERNAL_DOWNLOADS]: The skill contains multiple references to external documentation and best practices.
  • The skill points to a canonical source in the author's GitHub repository (mgifford/ACCESSIBILITY.md) for version control and reference.
  • Additional references are provided to established accessibility resources including the W3C Web Accessibility Initiative (WAI), WebAIM, and Drupal's accessibility standards. These are provided for informational purposes and do not involve the automated download of executable scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 07:03 PM
Security Audit — agent-trust-hub — tables