browser-smoke-review

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized system access were detected. The skill describes legitimate uses of browser automation tools like Playwright.
  • [PROMPT_INJECTION]: The skill possesses a potential surface for indirect prompt injection because it ingests and processes content from external websites.
  • Ingestion points: The skill processes content from target URLs, preview deployments, and rendered reports (SKILL.md).
  • Boundary markers: No explicit delimiters or boundary markers are defined to prevent the agent from interpreting instructions found on external pages.
  • Capability inventory: The skill uses browser automation for inspection, screenshot capture, and console/network monitoring.
  • Sanitization: No sanitization or filtering of external content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 11:12 AM
Security Audit — agent-trust-hub — browser-smoke-review