tables

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill instructs the agent to load and apply accessibility rules to HTML data tables within a project. This creates a surface for indirect prompt injection where malicious instructions could be embedded in the table data or attributes being processed.
  • Ingestion points: HTML table elements within the project's source code (referenced in SKILL.md).
  • Boundary markers: The skill does not define markers to separate data from instructions.
  • Capability inventory: The agent is tasked with reading, reviewing, and modifying HTML markup (referenced in SKILL.md).
  • Sanitization: No sanitization or validation logic is specified for the table content.
  • [SAFE]: The skill references configuration and guidelines from the W3C Web Accessibility Initiative (WAI), MDN Web Docs, and the Drupal project's official documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 01:03 AM