data-privacy-stack/presidio
Presidio is an open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data, leveraging NLP and customizable pipelines.
Awesome Infra for AI › AI Safety & Guardrails
toby-bridges/api-relay-audit
API Relay Audit is a command-line interface (CLI) tool for performing local security audits of AI API relays and LLM proxies. It provides separate query families to audit for prompt injection, identify model substitution signals, and detect Web3-specific relay risks. The tool helps users assess the trustworthiness of third-party AI API relays, OpenAI-compatible proxies, or Claude-compatible proxies before deploying them for production traffic or sensitive agent workflows. It's designed to run locally, ensuring that API keys are only sent to the chosen relay URL. API Relay Audit generates structured Markdown reports with per-step findings and a final verdict indicating the security posture (LOW/MEDIUM/HIGH risk). Key functionalities include detecting prompt injection and extraction, identity consistency signals, context truncation, tool-call rewriting, error-response leakage, and SSE stream anomalies. It also identifies potential model substitution by analyzing model identity, stream, latency, and upstream channel signals. For Web3 applications, it includes wallet-sensitive probes to check for ETH transfer guidance, signed-transaction refusal, and private-key leak refusal. The project can also be integrated as an agent skill (e.g., OpenClaw, Hermes) to allow AI agents to audit a relay before interacting with it.
https://github.com/toby-bridges/api-relay-audit
Also in AI Safety & Guardrails
NVIDIA-NeMo/Guardrails
NVIDIA NeMo Guardrails is an open-source toolkit for adding programmable guardrails to LLM-based conversational applications, focusing on safety, security, and controlled dialog.
superagent-ai/superagent
Superagent is an open-source SDK providing safety features for AI applications, including prompt injection detection, PII redaction, repository scanning for threats, and red teaming capabilities fo...
Tencent/AI-Infra-Guard
AI-Infra-Guard is a full-stack AI red teaming platform providing comprehensive security analysis, vulnerability scanning, and jailbreak evaluation for AI ecosystems and LLMs.
microsoft/agent-governance-toolkit
AI Agent Governance Toolkit (AGT) provides policy enforcement, identity management, execution sandboxing, and reliability engineering to secure autonomous AI agents in production.
FailproofAI/failproofai
Observability and policy enforcement for AI agent harnesses, hooking twelve coding and chat harnesses to record every run and block dangerous tool calls before they execute.
protectai/llm-guard
LLM Guard is a comprehensive open-source security toolkit designed to fortify Large Language Model (LLM) interactions by providing robust sanitization, malicious content detection, data leakage pre...
lennney/stop-that-shit
Multi-platform hook and skill guard for AI coding agents that blocks unrequested work such as generated hashes, checksums and task-scope expansion at the harness hook boundary.