🧠 AgentNull: AI System Security Threat Catalog + Proof-of-Concepts
AgentNull: AI System Security Threat Catalog + Proof-of-Concepts. Collection of PoCs for using Agents, MCP, and RAG in bad ways.
Directory
AgentNull: AI System Security Threat Catalog + Proof-of-Concepts. Collection of PoCs for using Agents, MCP, and RAG in bad ways.
Pre-execution enforcement and tamper-evident audit trails for AI agents. Hash-chained action logs, Ed25519 signatures, covenant policy language. EU AI Act…
Cryptographic proof-of-commitment protocol for MCP. Make verifiable commitments before posting/acting, preventing post-hoc narrative changes.
Cryptographic audit trail for AI agents via Model Context Protocol. Every AI decision signed Ed25519, hash-chained, tamper-proof. AISS-1.0 compliant…
This repository demonstrates a variety of **MCP Poisoning Attacks** affecting real-world AI agent workflows.
TurboPentest is an agentic AI penetration testing platform built by IntegSec that makes professional-grade security assessments accessible to every…
Proof-of-Work + Lightning Network authentication for AI agents. Wraps paid MCP tools with L402-signed receipts.
Headless browser with SHA-256 hash-chained audit trails and Ed25519-signed proof bundles. MCP server for AI agents.
Cryptographic runtime governance for AI agents. 20 tools. Sealed policy artifacts, continuous measurement, tamper-evident proof. Ed25519 + SHA-256.
Security scanner for developers and startups.
Audits a GitHub repository's stargazers for signs of fake-star injection across five deterministic axes (burst, suffix-farm, sequential-id cluster, same-second…
Formally verified AI safety APIs for autonomous agents. 75+ endpoints, x402 USDC micropayments, MCP server, A2A protocol. No signup required.
Verifiable document intelligence for AI agents. Extract, summarize, translate, claim-check, and notarize PDFs & URLs. Evidence bundles with cryptographic…
Integrates with Amazon Bedrock's Nova Canvas model to generate images from text descriptions with customizable parameters like dimensions and seed control.
Governance and audit layer for MCP tool calls. TrustLoop intercepts every AI agent action, logs it to a tamper-evident audit trail, blocks unsafe tools via…
A height-compressed, sublinear-space STARK prover. Designed to make very long zero-knowledge proofs practical on fixed-memory hardware (CPUs, GPUs, & edge…
AlienVault/USM Anywhere MCP Server - Threat intelligence and security monitoring
Trust ratings for AI agents and websites. Look up an agent's reputation, scan a site's AI-trust-readiness, and verify signed scorecards in-band — reads are…
MCP configuration to connect AI agent to a Linux machine.
420+ deterministic fintech tools - agentic payments (AP2, x402, Visa TAP, A2A), AML/KYC, BaaS comparison, MCP dev tooling - with 15 flagship tools as…
Integrates with Jira's REST API to enable issue management, task creation, and project tracking capabilities.
Scan website GDPR compliance: cookie consent, privacy policy, trackers. Score 0-100. -- x402 micropayment API + MCP server for AI agents
Integrates with Keycloak Admin to provide streamlined user and realm management operations for identity and access control automation.
# SafetyCulture MCP Server A Model Context Protocol (MCP) server for the SafetyCulture API. This project allows users to ask natural language questions about…