agent-first-screenshots

Warn

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: MEDIUMREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The loadSharp function in both scripts/capture-verify.mjs and scripts/screenshot-verify.mjs dynamically resolves the sharp library by searching the filesystem for specific .pnpm directory structures and importing from computed paths at runtime.
  • [REMOTE_CODE_EXECUTION]: The scripts/capture-verify.mjs script accepts a preCapture parameter which is executed as an arbitrary JavaScript string in the browser context via the Runtime.evaluate method of the Chrome DevTools Protocol (CDP).
  • [DATA_EXFILTRATION]: scripts/capture-verify.mjs initiates a WebSocket connection to an arbitrary wsUrl provided as a command-line argument, which could be used to facilitate communication with untrusted endpoints.
  • [PROMPT_INJECTION]: The preCapture feature creates a surface for indirect prompt injection, as an agent could be manipulated by the content of a target application to execute malicious JavaScript in the browser session.
  • [COMMAND_EXECUTION]: The skill's operation depends on the execution of Node.js scripts that manage browser state, capture screenshots, and perform file system writes to specified and temporary paths.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 14, 2026, 03:33 AM