qe-accessibility-testing

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the analysis of external web content, which presents a surface for indirect prompt injection.
  • Ingestion points: The skill uses Playwright's page.goto() and automated Task definitions in SKILL.md to load and interact with external URLs.
  • Boundary markers: In SKILL.md, there are no explicit instructions or delimiters provided to prevent the agent from following directives potentially embedded in the processed web pages.
  • Capability inventory: Across SKILL.md, the skill leverages browser automation tools (page.evaluate, page.$$) and agent coordination frameworks (FleetManager, Task) to inspect UI elements and execute accessibility audits.
  • Sanitization: In SKILL.md, no specific sanitization or filtering logic is provided for the content retrieved from the target URLs.
  • [EXTERNAL_DOWNLOADS]: The instructions and code samples reference the integration of @axe-core/playwright and @playwright/test. These are industry-standard testing libraries for accessibility and browser automation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 06:16 PM
Security Audit — agent-trust-hub — qe-accessibility-testing