Search

Small local jailbreak and prompt-injection fixture set for tests. Python port of @mukundakatta/jailbreak-corpus-mini.

Track untrusted tool output before it enters prompts or actions. Python port of @mukundakatta/tool-result-taint.

Defense-in-depth proxy sandbox for AI agents

A lightweight Node.js wrapper for routing HTTP(S) traffic through Tor, including optional ControlPort circuit rotation.

Scan TypeScript AI agent code for unguarded tool calls — pip wrapper for diplomat-agent-ts

Project AIR: forensic reconstruction and incident response for AI agents. Turn agent traces into signed forensic records with BLAKE3 + Ed25519.

Enterprise Security Monitoring SDK for AI Agents - Secure any AI agent in just 3 lines of code with real-time threat detection, behavioral analysis, and separate logging and threat reporting for comprehensive security monitoring

AGent Based Access Control (AGBAC) is is an open, vendor-neutral security specification that defines how AI agents securely perform actions on behalf of humans using existing IAM technologies

The Pydantic-based Firewall for MCP Servers. Stops hallucinated tool calls, validates schemas, and sandboxes dangerous operations.

Authensor guardrail adapter for LangChain/LangGraph

A system-level defense framework for AI agents that intercepts and blocks indirect prompt injection attacks using strict instruction provenance and dynamic policy enforcement.

The firewall for AI coding agents — prevents secrets, PII, and credentials from leaking through Copilot, Claude Code, Cursor, and LangChain

A hardened, containerized environment for running Claude Code as an AI agent with access to local tools via the Model Context Protocol (MCP).

LangChain middleware integration for OWASP Agent Memory Guard — runtime defense against AI agent memory poisoning (ASI06)

Evidence-gated verifier for AI coding agents with local safety checks, hooks, checkpoints, deploy guards, and MCP tools.

Native safety hooks for Claude Code — blocks destructive commands, enforces tool-call budgets, guards file reads, masks secrets, and audits every agent action. Fail-closed C++ daemon with extensible rule engine.

Python SDK for EvalGuard -- evaluate, red-team, and guard LLM applications with drop-in framework integrations

Reverse proxy firewall + LLM Gateway for AI agents

Credential isolation for AI agents. Store, guard, and record — your agent never sees your API keys.

Static analyzer for prompt injection and confused-deputy risks in LLM agent code.