medusa-setup
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use npx for executing create-medusa-app and the medusa CLI. These tools are standard for the Medusa framework but involve the execution of packages retrieved from the npm registry.
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to use WebFetch to retrieve content from docs.medusajs.com and perform WebSearch for project scaffolding. 1. Ingestion points: WebFetch of documentation URLs and results from web searches defined in SKILL.md. 2. Boundary markers: Absent; no specific delimiters or instructions to ignore embedded commands within the fetched data are provided. 3. Capability inventory: The agent is granted access to Bash for command execution and Write/Edit for file system modifications. 4. Sanitization: Absent; the skill does not require validation or sanitization of the documentation content before the agent processes it.
Audit Metadata