skills/zuplo/tools/zuplo-guide/Gen Agent Trust Hub

zuplo-guide

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest documentation from external sources including local files and remote URLs to inform configuration.
  • Ingestion points: Documentation files in node_modules/zuplo/docs/ and remote resources at https://zuplo.com/docs/llms.txt.
  • Boundary markers: Not present.
  • Capability inventory: Modifying routes.oas.json and TypeScript modules in /modules/.
  • Sanitization: Not present for documentation content.
  • [EXTERNAL_DOWNLOADS]: The skill retrieves documentation and policy configuration metadata from vendor-controlled domains.
  • URLs: https://zuplo.com/docs/llms.txt, https://cdn.zuplo.com/portal/policies.v5.json.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 07:22 PM