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