browser
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The
eval.jsscript allows the agent to execute arbitrary JavaScript within the browser context. While required for complex automation, this provides a large attack surface if the agent is manipulated by external content. - [EXTERNAL_DOWNLOADS] (SAFE): The skill installs the
wspackage from the official NPM registry to handle WebSocket communication. This is a standard and expected dependency for CDP-based automation. - [PROMPT_INJECTION] (LOW): Indirect Prompt Injection vulnerability (Category 8). The skill interacts with untrusted external web content which can be used to mount attacks.
- Ingestion points:
nav.js(navigating to URLs),eval.js(reading page content),pick.js(metadata from DOM elements). - Boundary markers: Absent. The instructions do not specify delimiters or warnings for the agent to ignore instructions found within the browser data.
- Capability inventory: The skill allows full browser control (
eval.js), local file writing (screenshots), and network access (navigation via Chrome). - Sanitization: Absent. Web content is passed to the agent or executed in the browser context without filtering or sanitization.
Audit Metadata