medusa-admin
Pass
Audited by Gen Agent Trust Hub on Mar 31, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches live documentation and component information from Medusa's official website (docs.medusajs.com) and utilizes official vendor packages @medusajs/admin-sdk and @medusajs/ui.\n- [COMMAND_EXECUTION]: Instructs the agent to use standard CLI commands such as npx medusa develop for testing and verifying admin extensions.\n- [PROMPT_INJECTION]: The skill defines an indirect prompt injection surface by instructing the agent to fetch external data and use it for file modifications. Given the trusted nature of the source, this is a standard development workflow.\n
- Ingestion points: External content fetched from docs.medusajs.com via WebSearch and WebFetch tools.\n
- Boundary markers: Absent; the skill does not provide specific instructions to delimit or ignore instructions within the fetched content.\n
- Capability inventory: The skill allows the use of Write, Edit, and Bash tools to implement changes based on documentation.\n
- Sanitization: Absent; the skill relies on the integrity of the vendor's official documentation.
Audit Metadata