skills/udecode/plate/dev-browser/Gen Agent Trust Hub

dev-browser

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user or agent to install the dev-browser package globally from the NPM registry.
  • [COMMAND_EXECUTION]: Includes instructions to run shell commands for installation and configuration, specifically npm install -g dev-browser and dev-browser install.
  • [PROMPT_INJECTION]: As a browser automation tool, the skill is susceptible to indirect prompt injection where malicious instructions are embedded in the websites being navigated or scraped.
  • Ingestion points: Navigating to URLs, filling forms, and scraping web data as defined in the description (SKILL.md).
  • Boundary markers: None provided in the skill instructions to distinguish between agent instructions and web content.
  • Capability inventory: Capabilities include navigating websites, form filling, taking screenshots, and data extraction (SKILL.md).
  • Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the web before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 01:31 AM