accessibility-auditing

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from external web pages via the browser_navigate and browser_snapshot tools in SKILL.md. This data could contain malicious instructions designed to mislead the agent.
  • Ingestion points: External web content retrieved from user-specified URLs.
  • Boundary markers: The skill does not define specific delimiters to separate the retrieved page content from its internal logic.
  • Capability inventory: The skill utilizes browser navigation, DOM/ARIA snapshots, and simulated keyboard events.
  • Sanitization: There are no instructions for sanitizing or filtering the content of the accessibility tree before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 09:42 PM