Prompt-injection firewalls & guardrails

Edge or API-deployed LLM firewall that blocks prompt injection, jailbreaks, toxic output and data exfiltration.

Configurable safeguards for Bedrock and other models: content filters, denied topics, PII redaction and prompt-attack detection.

Azure service that detects user prompt attacks and indirect (document) prompt injection.

WAF detection that flags prompt injection, PII and unsafe topics in AI application traffic at Cloudflare's edge.

Runtime guardrails for generative AI apps; calypsoai.com now redirects here.

Google Cloud service that screens prompts and responses for prompt injection, sensitive data leaks and harmful content.

Open-source framework and validator hub for checking and correcting LLM inputs and outputs.

Real-time API that screens LLM inputs and outputs for prompt injection, data leakage and policy violations.

AI security platform for visibility, control and protection across AI models, agents and apps.

Security toolkit of input/output scanners for LLM interactions. Repository is archived (read-only).

Open-source toolkit for adding programmable guardrails (topic, safety, jailbreak rails) to LLM apps.

AI gateway and guardrails that protect agents and apps from attacks, hallucinations and data leaks.

API services for securing AI apps, including prompt-layer guardrails and data redaction.

Security platform for employee and homegrown GenAI use: prompt protection, data leak prevention and AI usage visibility.

Meta's set of open tools to assess and improve LLM security, including Llama Guard classifiers and LlamaFirewall.

Python library and API that scans LLM inputs for prompt injection and jailbreaks. Last code push Jan 2024.