security 52

Sandbox-first automatic permission policy for DeepSeek Harness

Read-only security & compliance toolkit for DeepSeek Harness: prompt-injection detection (rule engine with a pluggable model classifier), Chinese-PII and structured-JSON redaction, and a local configuration security audit that emits redacted, reproducible

Auto mode for DeepSeek Harness (dsh): an Auto entry in the Permissions selector whose approval prompts are answered by OpenGuardrails policy instead of a human — plus the full OGR guard engine underneath. No core changes.

为 DeepSeek Harness 增加介于 Workspace Write 与 Full access 之间的自动批准权限档：例行沙箱升级由分类模型一次性放行，危险或不确定的操作仍转人工审批。An auto-approval permission preset for DeepSeek Harness between workspace-write and full access: routine sandbox escalations are granted once by a classifier

Application-layer authentication plugin for the dsh web surface

🛡️ 给 DeepSeek Harness 插件拍 X 光 —— DSH 插件安全体检与健康检查。静态启发式审计:代码执行、凭据访问、外传端点、混淆、安装脚本、bundle 清单合规,输出 0-100 风险分与裁决。Plugin security & health scanner for DeepSeek Harness: heuristic static audit (code execution, credential access, exfiltration, obfuscation, insta

装插件前，先体检：第三方插件 = 进程内全权限代码，这个工具让'盲装'变成'知情安装'——恶意模式、越权路径、未检查依赖，一目了然。Static heuristic vetting for third-party DeepSeek Harness plugins: exfiltration, credential access, over-privileged paths, unvetted dependencies.

Prompt-injection, jailbreak, and secret-leak detection with allow/ask/block interception for DeepSeek Harness: an Aho-Corasick pattern engine and heuristics ported from the Prompt-Injection-Payloads, Jailbreak-Detector, and Secret-Key-Leaker-Detect assets

PII masking middleware for DeepSeek Harness: anonymize names, phones, emails, ID cards, bank cards, keys, and addresses to placeholders before they reach the model, restore them at the display layer, keep the restore table only in memory and a controlled

Provider plugin for dsh-skill-pack-security: registers the pack's skills/ (zh) or skills-en/ (en) edition on ctx.skills AND the plugin_vet supply-chain gate tool on ctx.tools (license/SBOM/commit-lock/malware scans + five-dimension risk card). Ships both

DeepSeek Harness plugin for SecurStack security scans, policy checks, doctor diagnostics, and JSON CLI results.

Hold a DeepSeek Harness agent to a capmark capability manifest: mask its tools and judge every call.

Static bundle form of the DSH plugin-install security gate: reviews cordis_define/cordis_run with a fail-safe policy, plus review/audit tools and a browser approval popup (agree / agree+whitelist / reject; agree+whitelist writes the plugin family into tru

Pre-install supply-chain poison scanner for DeepSeek Harness plugins: AST analysis (NodeSecure JS-X-Ray) + deobfuscation decoder + regex heuristics to catch credential exfiltration, dynamic code execution, obfuscated imports, and install-time scripts.

Fail-closed LLM-assisted approval reviewer for DeepSeek Harness

DSH 规则执行引擎 v3：容器解析 AGENTS.md + 理解器 + 匹配机 + 执行框架

Minimal Root-Orchestrator PTES pentesting plugin for DeepSeek Harness

DeepSeek Harness community Bundle for the skill-security-guard static scanner

面向多 Agent、多模型、多 Provider 的 AI Coding Agent 安全配置中心

Enterprise compliance for DeepSeek Harness — SOC2/GDPR automated checks, sensitive-info redaction, and a redacted tool audit trail. · DSH 企业级合规插件：SOC2/GDPR 自动化合规自检、敏感信息拦截与脱敏、操作日志审计追溯。

DeepSeek Harness 插件：为 Agent 增加 code_scan 工具，用 semgrep 扫描代码并输出按文件/行号/严重级别分组的中文报告

One install for SpecFlow, GitFlow, Guardian, and Code Intel on DeepSeek Harness.

Plugin insight center — one answer to '哪些值得装': requirement matching (plugin_guide), environment recipes (recipe), health scoring (plugin_rank), static security scanning (plugin_audit), and a single install verdict (plugin_verdict)

Transport-layer data masking for deepseek-harness (dsh): sensitive values never leave the process — the model sees placeholders, you see real values restored live in the stream.

Password gate for dsh-web: opening the web port requires a username/password login; account credentials are stored salted+scrypt-hashed and AES-256-GCM encrypted in a local config file under $DSH_HOME. Host-only cordis plugin, no dsh source changes.

Read-side SIEM forwarder for DeepSeek Harness: normalises session activity to OCSF and ships it

Structured code review skill for DeepSeek Harness -- bugs, security, performance, style

Agent-decided approvals for DeepSeek Harness: a workspace-write base permission mode where an independent approval subagent judges every sandbox escalation (risky operations are rejected), with a configurable approval model and an audit log in Settings.

Autonomous (auto) mode permission classifier for DeepSeek Harness: a Claude-Code-auto-mode-like classifier over tools/pre-execute and approval/request, a selectable 'auto' permission preset, LLM semantic judge, git checkpointing, agent discipline guidance

DSH plugin: strong password / diceware passphrase generator (password_generate).

密码工具：生成强随机密码、检测密码强度与信息熵

DSH 装插件安全守卫：装前 5 问提醒 + 直查 npm 官方户口本体检 + 归属核对 + 风险台账。只读，不拦截，中文人话报告。

DeepSeek Harness 权限规则引擎：hard/deny/ask/allow 四级规则（hard 高于全访问）、全局与 workspace 作用域、通配符路径保护、可视化草稿式编辑器，规则持久化于 settings.yaml

Security audit plugin for DeepSeek Harness: static permission profiling and a runtime sentinel for third-party plugins

Secure credential vault for DeepSeek Harness: store GitHub/npm/API tokens (secrets never leave the host), run gh/npm/npx/node/git with the token injected in the environment, and manage tokens from a Settings page.

Installation safety gate & data-protection guard for DeepSeek Harness: 60 static signature rules (31 high/24 medium/5 low) scan plugin sources for malicious install scripts, credential theft, obfuscation, persistence and network callbacks before 'dsh plug

Agent governance suite for DeepSeek Harness (enterprise companion): policy-based tool gating (allow/deny/ask), structured JSONL audit trail, and per-agent token quotas against the host token meter — state under $DSH_HOME/gov

Deterministic Runtime Execution Governance & Security Circuit-Breaker for DSH & Multi-Agent Workstations

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

依赖安全审计：扫描项目依赖的已知漏洞（OSV.dev）并检测过期依赖（npm registry），返回漏洞严重级/修复版本与升级幅度

Zero-interruption audit + fuse blocking for DeepSeek Harness. / 零打扰 Agent 审计与保险丝拦截插件。

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

Evidence-backed runtime nutrition labels for DeepSeek Harness plugins and tool namespaces

装插件全流程自动化:四重安全检查(版本/patch/工具名/供应链)+ 自动安装 + 自动重启 DSH | Safe one-shot DSH plugin installs: four checks + auto install + auto restart

SSRF-resistant HTTP(S) fetch provider for DeepSeek Harness

面向 DeepSeek Harness（DSH）的危险命令 + 密钥泄漏拦截插件。挂载到 `tools/pre-execute` waterfall，在工具解析前短路拒绝，被拦截的副作用不会发生。

敏感信息扫描：递归扫描代码库中的泄露密钥/令牌/私钥/硬编码密码，输出去敏感化的位置与严重级，提交前自查安全

Runtime security guard for DeepSeek Harness (DSH) — blocks command injection, SSRF, credential exfiltration, and destructive operations at runtime.

DSH 自制技能全家桶：dsh-verifier(产物自验证) + autotelic-evolution(进化引擎+DeLM教训) + dsh-injection-guard(注入防护) + dsh-team-orchestra(队长制协作) + dsh-grilling(对齐访谈) + dsh-context-language(领域语言) + dsh-delegation(委派) + viking-memory-guide(记忆)。安装后 8 个技能自动出现在 DSH 会话技能目录。

Codex-inspired managed approval for DeepSeek Harness: risk-based MCP review, one-time grants, explicit denials, and human fallback on reviewer failure.