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

DeepSeek Harness 破甲：让所有模型都能破甲，不同模型可换不同提示词；默认提示词面向国模「小码酱」。Jailbreak for every model — swap prompts per model. 求 Star 收藏 ⭐

A pre-execution guard for AI coding agents. It blocks destructive Git and file system commands, plus common attempts to access sensitive files, before a tool call runs. Supports Amp Code, Antigravity CLI, Claude Code, Codex, Cursor, DeepSeek Harness, Gemini CLI, GitHub Copilot CLI, Grok Build, Hermes Agent, Kimi Code, OpenClaw, OpenCode, and Pi.

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.

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.

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.

Prompt-injection, jailbreak, and secret-leak detection with allow/ask/block interception for DeepSeek Harness: an Aho-Corasick pattern engine and heuristics ported from the Prompt-Injection-Payloads, Jailbreak-Detector, and Secret-Key-Leaker-Detect assets

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

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.

DSH plugin - framework upgrade safety & plugin gating: contract pre-check, rollback point, auto-rollback on failure, evidence-based auto-disable; plus a multi-source plugin market. Unofficial. | DSH 插件：框架升级安全 + 插件门控——升级前契约预检、回滚点、失败自动回滚、有确证证据才自动禁用；另带多源插件市场。非官方社区项目。

Use ChatGPT Codex, Claude, Grok, Antigravity, Kimi, GLM, Cursor, Kiro, Copilot, Qwen, ERNIE, Spark, JetBrains, Perplexity, Replit, and Cody subscriptions as DeepSeek Harness LLM providers via OAuth.

Automatic provider/model fallback chains for DeepSeek Harness agents when LLM requests keep failing (retry exhausted, auth, quota, rate limit)

DeepSeek Harness coding-subscription OAuth: SuperGrok/Grok Build, ChatGPT Plus Codex, Kimi Code, Claude Code. Fixes AUTH API key is invalid, INVALID_REPLAY_STATE, grok-4.6 xhigh, Kimi Bearer vs x-api-key.

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

Use a Kimi Code membership in DeepSeek Harness through a dedicated Kimi subscription model route

Stata-MCP: A MCP server for integrating Stata into your agent loop with a safety-first design.

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

掌上 dsh — the standalone mobile surface for the dsh web GUI: scan-to-pair device trust, the /m/ phone UI, the /m/api RPC channel with realtime SSE mux bridge, and a polished desktop pairing panel. Extracted from dsh-remote-web-ui (M1, behavior-identical)

DeepSeek Harness 破甲一体化安全分析插件：Android · Web · Native · Protocol · Malware · AI-Security 全领域聚合（9 bundle + 1 preset）