chrome-cdp

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates arbitrary JavaScript execution within an active browser tab using the eval command and permits raw DevTools Protocol methods via evalraw. This provides a high level of control over the browser session.
  • [INDIRECT_PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection by retrieving and processing content from external websites (via html, snap, and shot commands). Maliciously crafted content on these pages could potentially influence the agent's behavior.
  • Ingestion points: Browser-derived data processed by the script in scripts/cdp.mjs and returned to the agent context.
  • Boundary markers: The skill instructions do not specify the use of delimiters or instructions to ignore embedded commands within the retrieved page content.
  • Capability inventory: Powerful browser automation tools including eval (JavaScript execution), nav (navigation), simulated input (click and type), and raw DevTools Protocol access (evalraw).
  • Sanitization: While arguments are JSON-encoded before being sent to the browser, the data retrieved from the web pages is not sanitized or filtered for embedded instructions before being provided to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 10:37 AM
Security Audit — agent-trust-hub — chrome-cdp