ui-neuro-ergo

Pass

Audited by Gen Agent Trust Hub on Mar 2, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: Utilizes evaluate_script to run auditing JavaScript in the browser and references pnpm build for verifying code compilation.
  • [PROMPT_INJECTION]: The skill has an autonomous loop that ingests data from external web pages, creating a vulnerability surface.
  • Ingestion points: Web page screenshots, accessibility tree snapshots, and source code.
  • Boundary markers: No instructions or delimiters are provided to the agent to ignore potentially malicious instructions in audited content.
  • Capability inventory: The agent can modify local files and execute scripts in a browser context.
  • Sanitization: There is no defined logic to sanitize or filter external data before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 2, 2026, 01:42 PM