medusa-admin

Pass

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides documentation and code skeletons for MedusaJS admin extensions. All patterns align with standard open-source development practices for the Medusa v2 platform.
  • [EXTERNAL_DOWNLOADS]: The instructions include fetching documentation and searching for component specifications from the official MedusaJS domain (docs.medusajs.com). These references target a well-known service provider and do not involve untrusted third-party code.
  • [PROMPT_INJECTION]: The skill documents an extension model that processes external data, creating a potential surface for indirect prompt injection.
  • Ingestion points: Data enters via the 'data' prop in widget components like 'src/admin/widgets/product-custom-widget.tsx'.
  • Boundary markers: The provided code templates do not include specific delimiters or instructions to prevent the agent from following directives embedded within the 'data' prop.
  • Capability inventory: The skill's environment includes potentially sensitive tools such as 'Bash', 'Write', and 'Edit'.
  • Sanitization: No input validation or sanitization logic is present in the provided boilerplate code to filter potentially malicious instructions in the entity data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 02:51 PM
Security Audit — agent-trust-hub — medusa-admin