seo

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes Python scripts (fetch_page.py, analyze_visual.py, capture_screenshot.py) to download and process content from user-provided external URLs.
  • [COMMAND_EXECUTION]: The skill executes JavaScript within a headless Playwright browser to perform visual analysis and capture screenshots for SEO reporting.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests and processes untrusted HTML content from external websites.
  • Ingestion points: External HTML and metadata fetched via fetch_page.py and analyze_visual.py.
  • Boundary markers: The skill does not explicitly define prompt boundary markers or "ignore instructions" wrappers for the ingested web content.
  • Capability inventory: The skill is authorized to use the Bash tool, perform file system writes for saving screenshots, and execute scripts in a browser environment.
  • Sanitization: The skill implements proactive sanitization measures, including blocking private/internal IP addresses (SSRF protection) and validating output paths to prevent directory traversal.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 02:07 AM