Prompt-injection firewall for AI agents
Block malicious web content before it reaches your AI.
5 followers
Block malicious web content before it reaches your AI.
5 followers
Hey Product Hunt! š Instead of relying on clever prompts (which can be bypassed), SafeBrowse enforces a hard security boundary between untrusted content and your LLMs. Key features: ā¢ 50+ prompt injection patterns detected ā¢ Policy engine for login/payment forms ā¢ RAG sanitization for vector DBs ā¢ Python SDK with sync/async support ā¢ Fail-closed: security cannot be bypassed We'd love your feedback! What security challenges are you facing with AI agents?
