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.

Complete reverse-skill (85 SKILL.md) as a DeepSeek Harness (dsh) Cordis plugin — reverse engineering, authorized pentesting and security research skill pack.

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.

Deterministic Runtime Execution Governance & Security Circuit-Breaker for DSH & Multi-Agent Workstations

Read-only security & compliance plugin for DeepSeek Harness: prompt-injection detection, Chinese-PII redaction, and local configuration audit with redacted, reproducible reports.

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.

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

Safe automatic permissions for DeepSeek Harness.

🚀 DeepSeek Harness 多通道远程访问与安全守护插件 | 局域网扫码直连、Cloudflare / 自建公网隧道、微信 / QQ / 飞书 / Telegram 机器人全生命周期对话 | 内置全协议访问安全认证、后台防篡改与容灾保命体系

Remote access for DeepSeek Harness: account/password auth + MFA (TOTP) login gate, signed session cookies, role-based access, in-browser directory picker, and a Settings page for account management.

基于dsh web实现的多种模式，目的是服务于redteam进行授权的安全研究，覆盖渗透测试、红队评估、代码审计等范围领域，请勿用于非法行为。（允许二开，赋予模块各位自己的业务逻辑，不定期完善逻辑与修复bug）

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

Server-grade gateway that turns DeepSeek Harness into a multi-tenant platform: remote access + auto HTTPS, subuser permissions & quotas, sandbox enforcement, encrypted auth, audit log.

Auditable, token-gated DeepSeek Harness remote gateway: mobile QR access, per-device sessions, Host/Origin rewrite, settings/credentials/directory support.

装插件前，先体检：第三方插件 = 进程内全权限代码，这个工具让'盲装'变成'知情安装'——恶意模式、越权路径、未检查依赖，一目了然。Static heuristic vetting for third-party DeepSeek Harness plugins: exfiltration, credential access, over-privileged paths, unvetted dependencies.

Fail-closed LLM-assisted approval reviewer for DeepSeek Harness

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

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

ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.

Use ChatGPT (Codex), Claude, and Grok (X Premium) subscriptions as DeepSeek Harness LLM providers — OAuth login in the web UI, no API keys

Use openai-codex models and image generation via ChatGPT OAuth for DeepSeek Harness.

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

Self-contained DeepSeek Harness (DSH) plugin for Provider/Auth login, model switching, image fallback, token/cost analytics, and same-port Web restart. Useful? A star helps.

面向 DeepSeek Harness（dsh）的渗透测试模式 @CloverSecLabs