visual-validate

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its interaction with untrusted web content.
  • Ingestion points: Untrusted data enters the agent's context through browser navigation to arbitrary URLs and the retrieval of data via list_console_messages and list_network_requests tools in SKILL.md.
  • Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to isolate browser-sourced data from the agent's core logic.
  • Capability inventory: The skill possesses the ability to interact with the browser (clicking, typing, hovering), capture screenshots, and perform accessibility audits.
  • Sanitization: There is no evidence of sanitization or filtering applied to the console output or network metadata before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 06:16 AM
Security Audit — agent-trust-hub — visual-validate