Plugins

基于 DeepSeek Harness 的 GitHub 插件静态安全审查预设，该项目代码由ai生成，主要框架由我搭建，通过“侦察员+审计员”双 Agent 协作、通过实验性ai自测攻防。主要功能有防死机上下文裁剪，有效防御投毒与提示词注入。包含21条安全红线、依赖树连坐排查与自动 YAML 校验，这是一名20岁非科班大学生的AI安全探索，欢迎大佬指导。本项目不能代替人工审计。请勿在生产环境或敏感凭证环境中使用。

在会话工具条挂按钮，点击后开新标签页管理提示词；点【注入】可在当前会话下一次模型 step 前注入 prompt 到 system prompt。

Scoped persistent memory for DSH: memory_save/search/replace/remove/list across global, user, project and failure scopes, DSH storage-domain persistence with secret and prompt-injection scanning, session-scope search, retention cleanup, and optional session-start injection; standing context via memory_pin/memory_pins/memory_unpin.

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.

Taints the agent when tool results carry untrusted content, gates the privileged calls that follow, and refuses credentials passed to network-capable tools in every mode.

Per-session system prompt injection for DSH: template library, per-session picker, default template for new sessions. 会话级系统提示词注入器：模板库、按会话选择、新会话默认模板。