verify-ui
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read browser console logs and analyze web content. This establishes an attack surface for indirect prompt injection where malicious instructions could be embedded in the data being processed.\n
- Ingestion points: Web page content, browser console logs, and network request data.\n
- Boundary markers: No delimiters or ignore-instructions are specified for the browser output.\n
- Capability inventory: The skill can execute local development scripts and utilize browser automation tools.\n
- Sanitization: No sanitization of captured browser data is requested.\n- [COMMAND_EXECUTION]: The skill directs the agent to locate and execute shell commands from project configuration files like
package.jsonto start development servers.\n- [DYNAMIC_EXECUTION]: The instructions suggest using or creating headless browser scripts for automation, which involves generating and executing code at runtime.
Audit Metadata