qe-visual-accessibility

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a command-line interface named aqe to execute visual tests, responsive design validations, and accessibility audits. This usage is aligned with the skill's primary purpose for the author proffesor-for-testing.\n- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it reads and processes data from external URLs during its auditing workflows.\n
  • Ingestion points: The skill accepts arbitrary URLs in SKILL.md via the aqe CLI and the accessibilityAgent.audit method.\n
  • Boundary markers: There are no specific boundary markers or instructions defined to prevent the agent from following potential instructions embedded within the audited web pages.\n
  • Capability inventory: The skill is capable of executing CLI commands and performing network requests to scan external sites.\n
  • Sanitization: The skill does not specify any sanitization or filtering logic to handle untrusted content from the target URLs.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 06:09 PM