cloudflare-browser-rendering

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: CRITICAL
Full Analysis
  • Category 2: Data Exposure & Exfiltration (SAFE): The skill provides templates for taking screenshots and scraping websites. While these involve navigating to user-provided URLs (SSRF), this is the primary purpose of the service. No credentials or sensitive files are accessed.
  • Category 4: Unverifiable Dependencies (SAFE): The skill references official Cloudflare packages. The version check script is a benign utility.
  • Category 8: Indirect Prompt Injection (LOW): The AI-enhanced scraper template processes external website content. Evidence Chain: 1. Ingestion points: Website HTML in ai-enhanced-scraper.ts. 2. Boundary markers: None. 3. Capability inventory: AI output is parsed and returned to user; no further tool execution is performed. 4. Sanitization: Input truncation is used.
  • Scanner Alert Analysis (SAFE): The 'browser.se' detection is a false positive on API property strings like browser.sessions found in documentation and code. No actual navigation to 'browser.se' is performed.
Recommendations
  • Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 17, 2026, 04:42 PM