#ai-security

Shannon is an AI pentester for web applications and APIs. It analyzes your source code, identifies attack vectors, and executes real exploits to prove vulnerabilities before they reach production.

Open-source AI Bill of Materials (AIBOM) scanner: inventories AI models, datasets, prompts, embeddings, vector DBs & RAG pipelines across code, containers & Kubernetes — with file:line evidence, load-time risk detection (poisoned pickle / Keras Lambda / unsafe torch.load) and NIST AI RMF / OWASP compliance mapping. CycloneDX · SARIF · JSON.

Static security auditor for AI-agent configuration: Claude Code, MCP servers, Cursor, Codex, Copilot, Gemini CLI and more. 109 rules, SARIF output, OWASP LLM Top 10 mapping.

A type-checker and contract layer for AI agent tool calls, deny-by-default, in-process, Pydantic-only. Strict argument validation, ghost-argument stripping, and self-healing retries for MCP servers and agent frameworks.

Open-source AI verification infrastructure for deterministic verification of LLM outputs, tool calls, code, schemas, and agent state before production execution.

Offensive security framework for AI agent infrastructure - recon, credential looting, model exfiltration, poisoning, and attack-path analysis across MCP, A2A, gateways, and AI services. BloodHound for the agentic stack.

Agentic sandbox enumeration: find security issues, and seed escape automation.

Authority control plane for autonomous work. EMILIA Gate enforces finite customer-owned mandates at protected executor boundaries; the open protocol keeps evidence verifiable.

Praxis Policy Engine (PPE)

Convert source code into a repository-scale structural model. Air gapped, zero dependencies, SARIF and SBOM outputs.

Self-hosted runtime control plane for AI agents. Observe or HITL approve or Block rogue tool calls before it executes: secret leaks, prompt injection, supply chain etc in a local dashboard. Agent agnostic (Claude, codex, langchain etc.)

Prompt Gate — privacy-first, on-device DLP for the AI era. Blocks unauthorized AI tools at the DNS layer and inspects content sent to approved tools for secrets/PII, entirely on-device.

Fast Rust engine for detecting and redacting PII and secrets — in prompts, code, and databases. OpenAI-compatible gateway, Postgres scanner, CLI, and WASM. 32× Presidio. Apache-2.0.

A zero-trust execution platform that safely bridges AI agents and infrastructure without surrendering data sovereignty

One scan for AI risk. `opena2a review` checks an AI project across credentials, shadow agents, MCP servers, and dependencies, returns a score, and routes each finding to the tool that fixes it. Open source.

Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor, Codex, and any AI tool can do on your machine.

Autonomous AI pentesting agents — real-time reconnaissance, vulnerability detection, and exploitation orchestration. Go + TypeScript.

Executable security regression testing for agentic applications and MCP-integrated systems.

Local-first endpoint sensor for AI coding agents. Hash-chained audit trail, MITRE-mapped sequence detection, DLP. Forwards to the SIEM you already run.

Active security scanner for A2A and MCP servers

AI data-isolation verification — prove no user or customer can reach another's data across 13 AI surfaces, with tamper-evident evidence anyone can verify.

Supply chain security for ML

The open standard for AI agent integrity. Evaluate, enforce, and prove that autonomous agents are adversarially coherent, environmentally portable, and verifiably assured.

Composable security scanning harness for agent skills

Scan AI components (MCP servers, agent skills, npm/PyPI packages) for malware & risky capabilities. Local, deterministic, evidence-anchored. Free & OSS.