browser-automation

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [Prompt Injection] (SAFE): The skill contains standard persona-setting instructions for a browser automation expert. No patterns were found that attempt to bypass AI safety filters or override core instructions.
  • [Data Exposure & Exfiltration] (SAFE): No sensitive file paths, hardcoded credentials, or unauthorized network communication patterns were identified.
  • [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill discusses libraries like Playwright and Puppeteer as concepts but does not include any commands to install packages or execute remote scripts.
  • [Obfuscation] (SAFE): No encoded content, hidden characters, or homoglyphs were detected in the markdown or metadata.
  • [Indirect Prompt Injection] (LOW): While the skill describes web scraping (a surface for processing untrusted data), it does not provide executable code or specific interpolation patterns that create a vulnerability surface. The 'critical' and 'high' severity labels in the 'Sharp Edges' table refer to script reliability, not security vulnerabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:34 PM