qe-visual-accessibility

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external content from URLs to perform accessibility audits (e.g., WCAG compliance) and visual testing. Ingestion points include the --url parameter in CLI commands and the url field in programmatic API calls within SKILL.md. While processing untrusted web content presents a potential attack surface, the skill is scoped to its primary purpose as a quality engineering tool and does not exhibit malicious exploitation or excessive privilege request behavior.
  • [COMMAND_EXECUTION]: The skill documentation includes examples of executing a local browser utility (vibium) and Node.js scripts (visual-diff.js) located in a relative path within the skill environment. These executions are necessary for the skill's functionality and are restricted to specific, defined operations for visual comparison.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 06:15 PM
Security Audit — agent-trust-hub — qe-visual-accessibility