yashandb-app-builder

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes untrusted user requirements to drive the generation and execution of application code and shell commands.
  • Ingestion points: User requirement communication defined in SKILL.md.
  • Boundary markers: None explicitly defined to separate user input from agent instructions.
  • Capability inventory: Shell command execution for service management in deployment.md and Docker operations in docker-setup.md.
  • Sanitization: No sanitization or validation mechanisms are specified for the incoming user data.
  • [COMMAND_EXECUTION]: The instructions automate the execution of shell commands on the host system to start backend services (using go run or uvicorn), launch frontend development servers (npm run dev), and manage Docker containers for the database environment.
  • [EXTERNAL_DOWNLOADS]: The skill initiates the download of external assets including Docker images from the yashandb/yashandb repository and various programming language dependencies (Node.js/Python). These resources are consistent with the vendor's provided technology stack.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 08:08 AM
Security Audit — agent-trust-hub — yashandb-app-builder