website-monitor

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [NO_CODE]: The provided files contain no scripts or executable code, only instructions and API mapping documentation.
  • [INDIRECT_PROMPT_INJECTION]: The skill inherently processes data from external websites as part of its primary monitoring function. This creates an indirect prompt injection surface which is standard for scraping-based utilities.
  • Ingestion points: External content and visual data are retrieved through the firecrawl_scrape and context_dev_capture_screenshot tools.
  • Boundary markers: The instructions do not include specific delimiters but require the agent to maintain a 'read-only' posture and separate factual observations from interpretation.
  • Capability inventory: Capabilities are limited to diagnostic and monitoring tools such as strale_ssl_check, strale_website_health, and strale_page_speed_test.
  • Sanitization: The instructions require the agent to cite sources and note evidence gaps, which helps ensure analysis is based on available metrics rather than embedded commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 11:31 PM
Security Audit — agent-trust-hub — website-monitor