Search

Local secret masking boundary for AI agents

AgentShield LangChain integration — callback handler for AI agent policy governance

A zero-trust SDK for anonymizing PII locally before sending prompts to LLMs and seamlessly rehydrating the response.

Capability-based IFC, streaming-native cascaded guardrails, and an eval-to-guardrail compiler for LLM agents.

Xuda Dashboard Controller Agent

Web-layer counter-recon honeypot against agentic LLM attackers — drops invisible-to-human, visible-to-LLM payloads into your Flask/HTTP responses to halt, stall, or fingerprint AI-driven penetration scans.

AI model: LayerFault/precision-benign-mcp-examples

CLI-first, agent-native HTTP intercepting proxy & bug bounty toolkit. Headless Burp Suite alternative for AI agents (MCP), penetration testers, and ethical hackers with declarative YAML scope enforcement.

⚔️ Autonomous red-team swarm for AI apps, agents & MCP servers — pentest your agent before someone else does.

Agentic LLM injection benchmark — VisorCorpus payload delivery, VisorSD target discovery, HIT/MISS matrix per vector

An Execution Isolation Architecture for LLM-Based Agentic Systems

A deterministic policy gate between an LLM agent and its tools: every call is allowed or denied by code before it executes, denied by default, and logged for audit.

Smallest outsider-readable proof path through AgentGate + MCP Firewall: governed write_file, independent on-disk verification, and inspectable audit artifacts.

AIShell-Gate -- deterministic policy layer for AI generated Unix command execution. Policy gateway for AI agents executing shell commands. MCP server for Claude Code & Cursor. Tamper-evident audit

Anonymizer Plugin for Presidio

Research constitution and specification framework for comparing independently governed AI judgments without transferring authority.

Route a CTRLRun APPROVE through the OpenAI Agents SDK's tool-approval interruption.

A general-purpose agent framework that self-updates skills, rules, ethics, and identity from experience

AI model: LayerFault/agent-mcp-contradictory-tool-annotation

Palimpsest is an LLM-assisted semantic code enhancement framework that bridges Ghidra decompilation and CodeQL database construction. It is optimized for IoT device firmware analysis and for generating CodeQL-buildable source code.