drive-chrome-cdp

Warn

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill operates by invoking the chrome-cdp CLI tool to interact with the browser over the DevTools Protocol. This requires the binary to be present on the system's PATH.
  • [DYNAMIC_EXECUTION]: The skill includes several features for runtime code execution within the browser context:
  • The eval command allows the agent to execute arbitrary JavaScript in the top frame of the browser.
  • The raw command provides an interface to execute any method within the Chrome DevTools Protocol.
  • The recipe system executes sequences of parameterized commands from external YAML files.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill exposes several vectors for accessing and potentially exfiltrating sensitive data from the user's active Chrome session:
  • Tools such as snap, grid, and text extract DOM and accessibility tree content.
  • The net and console commands allow reading of network traffic (including payloads) and browser console logs.
  • The screenshot and record features capture visual data from the user's screen.
  • The upload command allows the agent to read local files and submit them to web forms.
  • [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface where instructions embedded in processed web pages could influence the agent's behavior.
  • Ingestion points: Data is ingested via the snap, grid, text, find, html, and value commands in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands in external data are documented.
  • Capability inventory: The skill possesses high-impact capabilities including click, fill, eval, upload, and nav as described in SKILL.md.
  • Sanitization: There is no mention of content filtering or sanitization for the data retrieved from external URLs.
  • [REMOTE_CODE_EXECUTION]: While the skill does not directly download and execute scripts via the shell, the eval functionality permits execution of code in the browser. If the agent's logic is subverted by a malicious website (via indirect injection), this tool could be abused to execute malicious JavaScript in a user's authenticated session.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 19, 2026, 07:17 PM
Security Audit — agent-trust-hub — drive-chrome-cdp