control-ui

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides templates for generating and executing JavaScript scripts using the Playwright library to automate browser tasks. These scripts are run locally to interact with development servers or applications.\n- [PROMPT_INJECTION]: The skill's primary function involves the agent browsing and inspecting potentially untrusted web pages, creating an indirect prompt injection surface.\n
  • Ingestion points: Web pages and app UIs accessed via Playwright's goto and locator methods in SKILL.md.\n
  • Boundary markers: No specific delimiters are mandated to separate untrusted page content from agent instructions.\n
  • Capability inventory: The agent has the ability to execute generated scripts, write screenshot files to the local filesystem, and access local network services via CDP as described in SKILL.md.\n
  • Sanitization: The instructions do not specify any validation or sanitization for data extracted from the browser pages.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 11:52 AM
Security Audit — agent-trust-hub — control-ui