db-generate

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to execute a shell command npx medusa db:generate <module-name> using the Bash tool. This involves running the Medusa CLI tool (a vendor-owned resource) to generate code artifacts.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits a command injection surface by interpolating a user-provided variable (<module-name>) directly into a shell command string without specified sanitization or escaping mechanisms.
  • Ingestion points: User-supplied argument provided to the /medusa-dev:db-generate command.
  • Boundary markers: None identified in the prompt instructions to delimit the argument.
  • Capability inventory: The skill uses the Bash tool to execute commands in the environment.
  • Sanitization: No validation or sanitization logic is defined for the <module-name> input before it is passed to the shell.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 10:39 AM
Security Audit — agent-trust-hub — db-generate