dsh-safety-net
Self-protection guardrails for the DeepSeek Harness: protected-path interception, backup-before-destroy, CLI self-recovery commands, and strict sandbox defaulting
61 results
Self-protection guardrails for the DeepSeek Harness: protected-path interception, backup-before-destroy, CLI self-recovery commands, and strict sandbox defaulting
DeepSeek Harness bundle that routes real sandbox escalation prompts through a dedicated approval reviewer
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.
DSH plugin: block dangerous shell commands and secret leakage before execution (tools/pre-execute veto)
Auto 自动审批插件:DSH 中间档权限——信任目录内自动放行、危险操作人工确认(类别开关可调)
Maestro Guard — pre-execute safety gate: native DSH approval prompts, parsed command-surface rules, decision journal
Dangerous-operation policy, canonical output redaction, and security review for DeepSeek Harness.
Static and runtime security guard for the DeepSeek Harness: scans plugins and workspaces for malicious code, context injection and token waste (block/warn/clean), intercepts dangerous runtime tool calls and prompt steps, and exposes /scan, plugin_scan, the scan web panel and a user-managed allowlist. Fully static analysis — never executes scanned code.
A DeepSeek Harness (dsh) security plugin: blocks agents from reading or writing sensitive files (.env, credentials, key material), masks leaked secret-shaped values in tool results, keeps an audit journal, and exposes safe inspection tools that never print raw values.
A safety harness plugin for DeepSeek Harness (DSH): protected-path enforcement, trash-based safe_delete with undo, last-known-good composition snapshots, pre-restart composition checks, and an audit journal.
保险区 Vault Wall — 让 DeepSeek Harness 无法感知、无法触碰用户指定敏感路径的隔离墙插件(隔离墙 + 人在回路审批 + 执行后验证 + 循环纠正 + 可回滚规则)
DeepSeek Harness 隐私保护插件:监控本地 Privacy Gateway (:8317) 与 Qwen2.5-0.5B 小模型,管理凭据脱敏、豁免白名单与加密密钥,并提供带凭据保护的模型入口与部署按钮
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.
Approval guard for DeepSeek Harness: write/edit/editor/bash calls touching sensitive paths (.env, .git, SSH keys, .pem) and reads of SSH keys or certificates become an approval ask.
DeepSeek Harness plugin: predict (pre-install) and detect (post-install) duplicate @deepseek-ai/dsh-* copies, version drift, and vendored core services to prevent Symbol-key crashes like "Cannot read properties of undefined (reading 'prepare')".
Agent harness 配置系统:agents/skills/hooks/rules 四层分工、instincts 持续学习(自动学模式、聚簇成技能)、AgentShield 安全审计(secrets/权限/hook 注入/MCP 风险)、Unified Memory Vault 跨 harness 共享、GateGuard 破坏性命令门卫。受 affaan-m/ECC(185k★ MIT)启发。
One install for SpecFlow, GitFlow, Guardian, and Code Intel on DeepSeek Harness.
Egress policy for DeepSeek Harness: a host allowlist on web_fetch and web_search enforced at connect time, audit-mode by default, with OCSF Network Activity records
DeepSeek Harness 工具调用安全守卫插件:规则引擎拦截 + 路径白名单 + 敏感文件黑名单 + 人工审批 + 审计日志 + 侧边面板
DSH 危险命令守卫:通过 tools/pre-execute 门禁拦截 bash/pwsh 高危命令(rm -rf /、mkfs、dd 写设备、管道执行脚本、git push --force 等),支持分级策略(极高危始终拒绝 / 中危跟随全局 deny/ask/log)、用户自定义规则与白名单。
Local, zero-network, fail-closed secret preflight for DeepSeek Harness model requests.
Local, deterministic release risk checks for DeepSeek Harness.
Guard DeepSeek Harness PowerShell, file, image, and search tools on Windows with workspace, credential, approval, and audit policy.
LaTeX compile check and BibTeX lint/fill/audit tools for DeepSeek Harness and any agent.