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
PrismorSec/prismor
Prismor is a security solution specifically designed for AI coding agents, offering runtime protection against various threats. It acts as a set of security hooks that monitor and control agent actions, effectively addressing risks such as prompt injection, unintended destructive actions, secret exfiltration, privilege escalation, dependency manipulation, and supply chain vulnerabilities. The tool implements features like a policy engine, session logs, security audit capabilities, and a command-line interface. Key functionalities include install-time enforcement, IOC matching for supply chain security, network isolation with egress allowlists, and a 'Skill Scanner' for assessing agent skill risk. Prismor also provides 'Sweep & Cloak' for secret prevention, 'Hermes Agent Cloaking' for Hermes-specific secret management, and a 'Semantic Guard' for LLM-assisted prompt-injection defense. Additionally, it features 'Canary' honeytoken planting, IAM for agent identities, 'Scoped Agent' for task-specific rules, and 'Learning' for rule proposal based on session history. It aligns with OWASP Top 10 for LLM Applications, covering prompt injection (LLM01), sensitive information disclosure (LLM02), supply chain (LLM03), improper output handling (LLM05), and excessive agency (LLM06). Installation is flexible, supporting curl, integration via an agent's skill file (like CLAUDE.md), pip, or direct git clone.
https://github.com/PrismorSec/prismor
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.