dsh-adversarial-review
by mario03690
针对代码、MCP配置和系统提示的对抗性审查——每个发现都附带可复现路径和置信度;不可复现的标记为疑似,从未确认。
Adversarial review for code, MCP configs and system prompts — every finding carries a repro path and confidence; unreproducible ones are marked suspected, never confirmed.
安装
dsh plugin --profile web add github:mario03690/dsh-adversarial-reviewGitHub 源码安装:首次需按提示配置 allowBuilds 构建授权后重试
安装与环境配置指引、插件开发教程见 DSH 中文社区文档 ↗
安装即在你的机器上以你的权限运行第三方代码——它可读写文件、使用凭据、访问网络,DSH 的工具审批不会为插件代码加沙箱。「检测到 manifest」仅代表发现 dsh.bundle / dsh.plugin 清单,不构成兼容性或安全审查;安装前请审阅源码,不熟悉的插件先在不含密钥的环境试用。
README
Adversarial review for code, MCP configs and system prompts — every finding carries a repro path and confidence; unreproducible ones are marked suspected, never confirmed.
What & why
Not a scanner: it reviews code/config/prompts YOU provide, it does not attack third-party services. adversarial_review probes named surfaces (injection, trust boundaries, secret handling, side effects, idempotency, swallowed errors) — each finding with a repro path and high/medium/low confidence, and anything it cannot reproduce is downgraded to suspected, not presented as confirmed (the same honesty contract as our tables' arithmetic self-check). mcp_config_audit checks agent/MCP configs for over-broad grants, embedded secrets, unannotated destructive tools. red_team_prompt attacks your own system prompt and hands back hardening. Pass model to run on a flagship (Claude/Kimi K3/GPT via AllRouter).
Start with what_can_you_do — describe your task in any language, get the exact tool and a ready-to-run call.
Install
dsh plugin --profile <your-profile> add github:mario03690/dsh-adversarial-review
Thin config layer only (one @deepseek-ai/dsh-mcp-client row, shipped as cordis.patch.yml) — no tool code on your machine. Built against the dsh v0.1 developer preview's MCP client config shape (2026-08-13); if a later preview changes it, open an issue for a same-day fix.
Cost, quota, privacy
First heavy call is free (anonymous, no signup); afterwards billed at real upstream cost, reported in every response; failed calls are not charged. Bring an AllRouter key to run any tool on a flagship model at direct rates. The config URL carries ?s=dsh-dsh-adversarial-review — a channel tag identifying the install path, not you.
Disclosure: built and run by the team behind ainetcafe.com. Full bundle: dsh-netcafe. MIT.
Compatibility & permissions (at a glance)
| Signal | This plugin |
|---|---|
| Runtime | dsh v0.1 developer preview (2026-08-13, Cordis v4). Touches only the MCP client config shape — the narrowest surface available. Verified against a live endpoint on 2026-08-17. |
| What runs locally | Nothing. Ships one cordis.patch.yml row; there is no tool code, no build step and no lifecycle script in this package. |
| Filesystem access | None. |
| Shell / process access | None. |
| Network access | Outbound HTTPS to ainetcafe.com only, from the MCP client that dsh already ships. |
| Credentials | None required. No signup, no API key for the free tier. An optional AllRouter key, if you supply one, is sent by dsh as a request header and is never stored by us. |
| Data retention | Documents and prompts are processed in memory and not retained. |
| Dependencies | One peer dependency: @deepseek-ai/dsh-mcp-client (ships with dsh). |
| License | MIT (see LICENSE). |
| Publisher | The team that runs ainetcafe.com — our own hosted service, free tier plus paid usage. Issues get a same-day reply. |
A directory listing is not a security review. Read
cordis.patch.yml— it is short enough to read in full in under a minute.
原始 README: https://github.com/mario03690/dsh-adversarial-review/blob/main/README.md ↗
同类插件
查看全部 →
k8e
k8e.sh — 开源 Agentic AI 沙箱矩阵

hol-guard
开源AI代理防病毒:运行时拦截风险工具、秘密访问、提示注入、恶意软件包、MCP服务器、插件和技能。

anolisa
ANOLISA(Agentic Nexus Operating Layer & Interface System Architecture):具备运行时、安全性、可观测性和 Tokenless 响应压缩能力的 Agentic OS,可降低 Token 使用量与成本。

mobius
首个自我演进的开源 Agent OS:连接你的团队、AI agent、设备与算力

deepseek-harness-desktop
DeepSeek Harness Tauri 桌面版 | Only 5mb installer, zero environment setup. Windows / macOS / Linux.

open-managed-agents
开源Claude管理代理API实现和自托管Claude标签式代理运行时。即插即用;在Cloudflare Workers/Durable Objects或Node.js上运行。Apache 2.0。