cdn-cache-purge-tests

Pass

Audited by Gen Agent Trust Hub on Oct 2, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external CDN responses to verify cache status.
  • Ingestion points: HTTP responses from external URLs are retrieved via requests and Playwright in SKILL.md and references/browser-cache-control.md.
  • Boundary markers: Examples use specific JSON field assertions which provides a degree of delimitation.
  • Capability inventory: Provides network access and browser automation tools.
  • Sanitization: HTTP response content is parsed but not explicitly sanitized before use.
  • [COMMAND_EXECUTION]: The skill includes templates for curl and aws CLI commands to interact with CDN APIs, correctly using environment variables for tokens.
  • [EXTERNAL_DOWNLOADS]: References and connects to well-known service APIs and documentation sites (Cloudflare, Fastly, AWS).
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 2, 2026, 09:55 AM