dsh-adversarial-review

by mario03690

0 开发与运行时github未核验到 manifest收录于 08-16

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-review

GitHub 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

目录

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 ↗