next-dev-loop

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • Installation of Development Tools: The skill provides instructions to install agent-browser and upgrade Next.js using standard package managers. These steps are necessary for the development workflow and target official project repositories.
  • Shell Command Execution: Instructions include using shell commands to manage session IDs and environment variables. This is a common practice for maintaining persistence and state across automated browser sessions.
  • Processing External Content: The skill interacts with browser DOM data and Next.js server-sent events. This creates a surface area for indirect prompt injection where data from the application under development could influence the agent's behavior. Ingestion points include the agent-browser output and the Next.js MCP endpoint. While no specific boundary markers or sanitization steps are defined in the instructions, this is a standard characteristic of tools designed to introspect web applications.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 07:39 AM
Security Audit — agent-trust-hub — next-dev-loop