A Prompt-Injection Firewall for AI Agents and RAG Pipelines
A Prompt-Injection Firewall for AI Agents and RAG Pipelines
We built SafeBrowse — an open-source prompt-injection firewall for AI systems. Instead of relying on better prompts, SafeBrowse enforces a hard security boundary between untrusted web content and LLMs. It blocks hidden instructions, policy violations, and poisoned data before the AI ever sees it. Features: • Prompt injection detection (50+ patterns) • Policy engine (login/payment blocking) • Fail-closed by design • Audit logs & request IDs • Python SDK (sync + async) • RAG sanitization PyPI: pip install safebrowse Looking for feedback from AI infra, security, and agent builders.
Share cardActual performance
Launch Intel predictions
Analyze your own launch →Correct prediction on native model
Similar products
A Firewall for AI agents with auditing
Trajeckt, a Firewall for AI Agents
Demystifying Advanced RAG Pipelines
HELM — the execution firewall for AI agents
RAG Firewall – retrieval-time guardrails for LangChain/LlamaIndex
The Firewall for Humanity.
Bastiontrace – Forensics for prompt-injected AI agents
Build RAG pipelines that are optimized for your data.
Pipelines
Pipelines