curriculum-studio

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The architecture mandates a secure local API using per-run capability tokens and same-origin enforcement to prevent cross-site request forgery and unauthorized access in local network environments.
  • [SAFE]: Filesystem security is enforced through server-side document-ID-to-path mapping, symlink escape rejection, and atomic write operations (temp-file and rename) to ensure data integrity and prevent directory traversal.
  • [SAFE]: The skill explicitly prohibits the evaluation or execution of MDX modules and executable content during the parsing process, mitigating potential code execution vulnerabilities from curriculum files.
  • [SAFE]: Production isolation is a hard guardrail, with specific verification steps to ensure that studio-only logic, API endpoints, and filesystem-accessing Node.js modules are stripped from the production build.
  • [SAFE]: The design includes robust validation layers (syntax, schema, domain, and curriculum-specific tests) that must pass before any changes are committed to the disk.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 08:46 AM
Security Audit — agent-trust-hub — curriculum-studio