openchoreo-import

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes standard Kubernetes CLI tools including helm, kustomize, and kubectl to process and template source manifests.
  • [COMMAND_EXECUTION]: Spawns a local background process to run a Node.js-based preview server (server.cjs), which facilitates real-time visualization of the migration plan in a web browser.
  • [EXTERNAL_DOWNLOADS]: Retrieves technical reference data, component type indices, and module catalogs from the official vendor domain (openchoreo.dev).
  • [PROMPT_INJECTION]: Ingests untrusted external application manifests and charts (Step 2 in SKILL.md), which constitutes an indirect prompt injection surface if processed data contains malicious instructions meant to subvert the migration plan logic.
  • Ingestion points: Reads Helm charts, Kustomize overlays, and YAML files from user-specified paths.
  • Boundary markers: No explicit delimiter or 'ignore' instructions are used when interpolating manifest data into the planning context.
  • Capability inventory: Possesses capabilities to execute shell commands (helm, kustomize) and write/serve files locally via Node.js.
  • Sanitization: No specific content sanitization or validation is performed on the untrusted input data prior to analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 02:33 AM
Security Audit — agent-trust-hub — openchoreo-import