dsh-prompt-antivirus
Global prompt-injection / context-virus defense for DeepSeek Harness: scans tool arguments, tool results, pre-model messages and the outbound stream; quarantine/block/monitor modes, canary trap, and an evolvable on-disk signature library with learn/import/export.
全局提示注入 / 上下文病毒防御：扫描工具参数、工具结果、进模型前消息与出站流；隔离/阻断/监控三模式、金丝雀陷阱、可演进磁盘签名库（学习/导入/导出）。
How to install
dsh plugin add github:QinpanWan/dsh-prompt-antivirus About
dsh-prompt-antivirus — 全局防上下文病毒感染 运行时防御：扫描 · 隔离 · 金丝雀陷阱 · 人工门控 · 审计，覆盖 dsh 全部预设与子代理。 原理移植自 MIT 项目 openclaw-prompt-antivirus（github.com/QinpanWan/openclaw-prompt-antivirus），按 dsh（cordis）钩子面接线。 安装 sh dsh plugin --profile web add github:QinpanWan/dsh-prompt-antivirus 装完重启 dsh web 生效（日志出现 [prompt-antivirus] 已加载）。插件挂载在 profile 层， 对所有预设与子代理全局生效。源码安装 / 手动部署见文末「接入」。 问题 提示注入是 LLM 智能体的核心弱点：模型分不清「指令」与「数据」——藏在网页检索结果、文件内容、 [CRON TASK] / [SCHEDULE REMINDER] 到期文本里的恶意文字，可以悄悄改写行为、外传数据或执行破坏性操作 （即「上下文病毒」感染）。本插件在数据进入模型前后各加一道防线。 拦截点（dsh 钩子 ↔ OpenClaw 对照） | 防线 | dsh 钩子 | 行为 | | --- | --- | --- | | 工具参数扫描（直接注入） | to…
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 1
- mo. downloads
- –
- Last push
- 2026-09-08
- Created
- 2026-08-31
Links
Basic safety check
- Findings
- curated 收录但无 npm 包/安装命令
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- dsh, dsh-plugin, harmonyos, prompt-injection, security
Related plugins
dsh-auto-mode
NanmiCoder/dsh-auto-mode
Adds an Auto permission preset between Workspace Write and Full access: routine work stays in the official workspace-write sandbox while the current session model reviews escalation and destructive calls, granting one exact wider access once, asking when the intent is ambiguous, and denying critical paths.
dsh-passwords
slywalker2006/dsh-passwords
Turns DeepSeek Harness into a server-grade multi-tenant platform: remote access + auto HTTPS, subuser permissions & token/daily quotas, sandbox enforcement, encrypted auth & audit log.
sofagent
KongFangXun/sofagent/tree/main/engine/dsh-plugins/cordis-plugin-sofagent-audit
Commit-time audit harness for AI coding agents: 24 git-diff rules (secrets, out-of-scope edits, prompt injection), HMAC-signed audit trail, snapshot rollback, and an MCP server with 84 tools. Installable via dsh plugin add.
dsh-vault
Ox0400/dsh-vault
Encrypted local credentials vault for the Harness: a web settings page and vault_* tools to store, search and copy passwords, API keys, TOTP secrets and card data, with health audits, expiry rotation, imports/exports and read-only/ask access modes.