Bundle
upstream-radar
Always-on dependency and compatibility monitoring for DeepSeek Harness plugins, including exact paths, upstream changes, and isolated install/load evidence.
MicroMilo238
Browse
5 results
Skill
skill-security-guard
Scan agent skill packages for static security risks. Use for skill audit, security check, prompt-injection review, suspicious scripts, unsafe dependencies, zip package review, and pre-install skill review. Not for runtime monitoring.
rrrrrredy2
Bundle
dsh-prompt-antivirus
全局提示注入 / 上下文病毒（context virus）防御插件：tools/pre-execute 扫工具参数、tools/post-execute 扫工具结果、agent/pre-step 扫进入模型前的消息并注入金丝雀守卫、llm/stream 出站消毒；支持 block / quarantine / monitor 三模式、磁盘化可演进病毒库（学习/导入/导出）与审计日志。纯 JS 无原生依赖，profile 层挂载，对所有预设与子代理全局生效。
QinpanWan1
Bundle
@bryan-cmf/dsh-infra-observability
DSH-Plugin: structural observability layer — real tool/skill usage recording (tools/result), skill-catalog audit, and a watchdog with health/error events. No model self-reporting.
Bryan-cmf1
Bundle
dsh-error-audit
DeepSeek Harness 实时 AI 自审插件：报错/警告连同时间、错误码、会话、用户原话、AI 动作与工作区写入日志目录，并主动通知 AI
1667671