Back to Home
sachinlathiya icon

Cerina-Protocol

Verified Safe

by sachinlathiya

Overview

Collaboratively drafts, critiques, and finalizes Cognitive Behavioral Therapy (CBT) exercises using a multi-agent LangGraph backend with a mandatory human-approval gate.

Installation

Run Command
docker-compose up --build

Environment Variables

  • OPENAI_API_KEY
  • CHECKPOINT_PATH

Security Notes

The code does not use 'eval' or other direct code execution vulnerabilities. Hardcoded secrets are not present; API keys are expected via environment variables. The primary security considerations for this type of application are related to potential LLM prompt injection (where the LLM might generate undesirable content if the 'intent' is adversarial, though the system includes safety and clinical review agents to mitigate this) and the default permissive CORS setting (`allow_origins=['*']`) which should be tightened for production deployments.

Similar Servers

Stats

Interest Score0
Security Score8
Cost ClassMedium
Avg Tokens1950
Stars0
Forks0
Last Update2025-12-22

Tags

Agentic AILangGraphCBTHuman-in-the-loopFastAPI