ego-browser

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPRIVILEGE_ESCALATION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The macOS installation script (scripts/install.sh) downloads the ego lite application DMG from the vendor's CDN at https://cdn.ego.app. This is a necessary component for the skill's functionality.
  • [COMMAND_EXECUTION]: The skill relies on the Bash tool to execute ego-browser nodejs commands. These commands utilize heredocs to pass JavaScript directly to the browser automation runtime, enabling arbitrary browser control within the Chromium environment.
  • [PRIVILEGE_ESCALATION]: The installation process for macOS (scripts/install.sh) uses sudo to perform administrative tasks, including moving the application to the /Applications folder, removing Gatekeeper quarantine attributes (com.apple.quarantine), and executing system package installers.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to scrape and interact with arbitrary web content, which exposes the agent to instructions embedded in third-party websites.
  • Ingestion points: Web data enters the agent context through page.snapshot(), accessibility tree reads, and targeted DOM extraction in tools like learnings/google/tools/search-extract.js and learnings/x-com/tools/timeline.js.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the provided extraction scripts.
  • Capability inventory: The skill possesses the ability to execute shell commands via the Bash tool, perform network requests via fetch, and write to the filesystem through screenshot and screencast features.
  • Sanitization: The provided scripts extract raw text (e.g., via innerText) from the DOM and return it to the agent without filtering or sanitizing potential prompt injection vectors.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 06:26 PM