skills/adobe/skills/browser-probe/Gen Agent Trust Hub

browser-probe

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill performs its stated function without any malicious intent or security vulnerabilities. It is authored by a known vendor and contains no obfuscation or suspicious code.
  • [COMMAND_EXECUTION]: External commands are executed using execFileSync with argument arrays in scripts/browser-probe.js. This is a secure method that prevents shell command injection.
  • [EXTERNAL_DOWNLOADS]: The skill relies on playwright-cli, a reputable tool. Instructions guide users to install it from the official NPM registry, which is a well-known service and a trusted source for development tools.
  • [SAFE]: Regarding indirect prompt injection, the skill ingests external data (page titles and headers) in scripts/browser-probe.js for diagnostic purposes. This ingestion is bounded by regex filtering and structured report generation, which mitigates the risk of the data containing instructions that could override agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 09:02 AM
Security Audit — agent-trust-hub — browser-probe