DeepSeek Harness 权限规则引擎：hard/deny/ask/allow 四级规则（hard 高于全访问）、全局与 workspace 作用域、通配符路径保护、可视化草稿式编辑器，规则持久化于 settings.yaml

AI Agent runtime authorization & evidence verification — tool-call GuardrailProvider, CCS 7-dimension verification standard, MCP/DSH security scanner, SSRF/command-injection/credential-exfil blocking with Ed25519 signed receipts.

Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks.

A macOS-only native account-pool and provider plugin for DeepSeek Harness.

Always-on dependency and compatibility monitoring for DeepSeek Harness plugins, including exact paths, upstream changes, and isolated install/load evidence.

DeepSeek Harness auth插件

DeepSec — AI Security Offense & Defense Platform. Shield audits AI-generated code for hallucinated packages, missing safeguards & AI pattern errors in real time. Spear automates authorized penetration testing with 40+ skill packs, from recon to PoC.

Open-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.

The vendor-neutral protocol for AI agent safety & security — and the neutral benchmark that ranks the vendors.