返回目录

GITHUB TOPIC

security

18个项目包含此标签

18 个项目

GitHub Topic 精确匹配

安全与治理

Read-only security & compliance plugin for DeepSeek Harness: prompt-injection detection, Chinese-PII redaction, and local configuration audit with redacted, reproducible reports.

已验证
auditdeepseek-harnessdshdsh-plugin
安全与治理

让你通过浏览器安全地远程使用 DeepSeek Harness:登录、MFA 两步验证、角色权限和远程文件预览。 | Use DeepSeek Harness securely in a remote browser with login, MFA, roles, and remote file preview.

已验证
authenticationdeepseek-harnessdsh-pluginmfa
安全与治理

dsh-passwords

slywalker2006

Server-grade gateway that turns DeepSeek Harness into a multi-tenant platform: remote access + auto HTTPS, subuser permissions & quotas, sandbox enforcement, encrypted auth, audit log.

已验证
authenticationdeepseekdeepseek-harnessdsh
安全与治理

dsh-one-gateway

TiantianFlow

Private DSH One Gateway — loopback, identity-first ingress for DeepSeek Harness

已验证
deepseek-harnessdshdsh-pluginremote-access
安全与治理

Fail-closed export-copy redaction for DeepSeek Harness session telemetry

已验证
deepseek-harnessdsh-pluginprivacyredaction
安全与治理

该仓库暂未提供项目说明。

已验证
deepseek-harnessdsh-pluginpermissionssecurity
安全与治理

AI approval answerer for DeepSeek Harness (DSH) using the unified LLM route with fail-closed policy checks.

已验证
agent-harnessapprovalcordisdeepseek-harness
开发工具

SecurStack adapter for DeepSeek Harness: run repository security scans, policy gates, doctor diagnostics, and JSON CLI results from safe AI-agent tools.

已验证
ai-agentscontainer-securitydastdeepseek-harness
Agent 与会话

Solve the AI goldfish brain: auditable personal memory for DeepSeek Harness - preferences, project conventions, workflows, error lessons. 解决 AI 金鱼脑的本地可审计记忆层。

已验证
deepseek-harnessdsh-pluginmemorypersonal-knowledge
安全与治理

🔒 12-method security audit for Hermes Agent — virus scan, rootkit detection, SSH brute force protection

已验证
ai-agentsauditdeepseek-harnessdsh-plugin
安全与治理

dsh-mcpguard

ChenLaoshiYF

?? for DeepSeek Harness: first security plugin for dsh. Scans skills/MCP configs for prompt injection, homoglyphs, hidden Unicode, dangerous shell, credential leaks. DSH ????????

已验证
ai-agentdeepseek-harnessdsh-pluginllm-security
安全与治理

DeepSeek Harness (dsh) 插件:Workspace Only 开关 —— 任何模式下越界文件访问都请求用户确认 (approval prompt in every mode)

已验证
deepseek-harnessdshdsh-pluginpermission
开发工具

Task-to-skill pairing for DeepSeek Harness — pours the minimal set (usually one; zero when plain tools suffice), prefers workflow skills over hand-composed atomics. Laziness ladder, quarantine → SkillSpector scan → explicit human approval, never auto-installs. 任务配技能 · 懒惰阶梯 · 安全酒窖 · 绝不自动安装

已验证
agent-skillsclaude-codecodexdeepseek-harness
安全与治理

Runtime security gate for DeepSeek Harness: egress host allowlist, secret redaction in tool results, and an append-only audit log

已验证
cordisdeepseek-harnessdshdsh-plugin
安全与治理

DSH plugin gate + clinic: static audit before and after install, hash lock, peer search, mechanical detox. Never executes the target plugin.

已验证
auditdeepseek-harnessdsh-pluginsecurity
安全与治理

DSH LLM response-stream injection filter: hard-block rare Unicode scripts (Track A) + score-based disposal of control chars / protocol markers / script mixing / spam keywords (Track B) on the llm/stream waterfall. Install: dsh plugin --profile web add github:XiaoYuOvO/dsh-llm-injection-filter

已验证
cordisdeepseek-harnessdshdsh-plugin
安全与治理

dsh-mcp-security

已验证
deepseek-harnessdsh-pluginmcpmcp-security
安全与治理

Dependency supply-chain hygiene audit for DeepSeek Harness (dsh): peer-range resolvability, broken dist-tag detection, stale/missing-license/non-registry deps, installed-vs-declared drift. Complements dsh-poison-guard and dsh-plugin-doctor.

已验证
deepseek-harnessdependency-auditdsh-pluginnpm