dsh-injection-guard
面向 DSH 的来源感知提示词注入防护：跟踪 Turn 中的不可信上下文，检测注入信号，评估敏感 Sink，并通过可解释审计日志阻断高风险工具调用。
Source-aware prompt injection guard for DSH: tracks untrusted turn context, detects injection signals, scores sensitive sinks, and blocks high-risk tool calls with explainable audit logs.
怎么安装
dsh plugin add dsh-injection-guard 简介
dsh-injection-guard English | 中文 Source-aware prompt injection protection for DeepSeek Harness. **v0.1.0 status:** installable DSH bundle, turn-level source tracking, deterministic injection signals, sensitive-tool interception, explainable risk scoring, localized audit logs, and reproducible DSH integration fixtures. Coding agents read files, web pages, tool results, skills, and other external content. That content can contain instructions aimed at the agent. dsh-injection-guard tracks untrusted context and blocks sensitive tool calls when indirect prompt injection is suspected. text untruste…
推荐参考
信息
- 协议
- MIT
- 语言
- TypeScript
- GitHub 星标
- 1
- 月下载
- –
- 最近更新
- 2026-08-21
- 创建于
- 2026-08-19
基础安全检查
- 检查结果
- 无
- 收录来源
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- 主题标签
- cordis, deepseek-harness, dsh-plugin
同类推荐
loki-mode
asklokesh/claudeskill-loki-mode
多代理自主 SDLC 框架。从规格到部署应用。PRD、GitHub issue、OpenAPI/JSON/YAML 或一行简报。5 个 AI 提供商，8 个质量门。
ccmanager
kbwo/ccmanager
用于Claude Code / Gemini CLI / Codex CLI / Cursor Agent / Copilot CLI / Cline CLI / OpenCode / Kimi CLI的编码代理会话管理器。
langfuse
langfuse/langfuse
🪢 开源AI工程平台：LLM评估、可观测性、指标、提示管理、游乐场、数据集。与OpenTelemetry、LangChain、OpenAI SDK、LiteLLM等集成。🍊YC W23