dsh-gpt-compat
Fail-closed DSH compatibility guard for redundant GPT/Codex sandbox escalation arguments
408 results
Fail-closed DSH compatibility guard for redundant GPT/Codex sandbox escalation arguments
拒绝 AI 味的 UI 设计:21 主题 + 四动词(构建/audit 审计/redesign 重构/study 提取 DNA)+ 57 个 slop 测试门 + 预输出自我批评——拒绝所有 LLM 训练成的分布默认值。受 Nutlope/hallmark(25.8k★ MIT)启发。
VulnClaw + DeepSec 桥接插件:AI 安全 CLI(授权渗透测试 / Shield 代码审计)→ dsh 工具 + 设置页安全工具台 UI
DSH LLM response-stream injection/pollution filter: hard-block rare Unicode scripts (Track A) and score-based disposal of control chars / protocol markers / script mixing / spam keywords (Track B) on the llm/stream waterfall.
Strip sandbox_permissions / justification from model tool-call arguments so sandbox escalation is never triggered when the session already has sufficient permission.
AgentENV execution-world bundle for DeepSeek Harness
Access-password gateway plugin for DeepSeek Harness Web: every request on the gateway port requires authentication (no unauthenticated surface besides the login/setup page), first visit sets the password, and it can be rotated from the dedicated Security settings page.
Stavros RedTeam for DeepSeek Harness (DSH) — authorized red-team persona + scope-guarded pentest tooling (persona, 24 subagents, methodology and 78 zero-dependency guard tools).
Find DSH plugins and security-scan them before install
DSH Web GUI plugin: session-scoped "Allow for this session" option in the approval dialog (per-mode standing grants, localStorage)
Enterprise-grade Zero-Trust Authentication, LAN/Public Access Control & Security Gate Plugin for DeepSeek Harness (DSH).
Self-protection guardrails for the DeepSeek Harness: protected-path interception, backup-before-destroy, CLI self-recovery commands, and strict sandbox defaulting
Model-visible redaction plugin for DeepSeek Harness: redacts secrets from model input and output streams
DSH web plugin: play a notification chime when the agent asks the user a question (ask_user_question / plan review) or requests approval (sandbox escalation, tool approval).
Native Auto Review for DeepSeek Harness with automatic host compatibility selection
安装任何第三方 DeepSeek Harness (DSH) 插件或 agent preset 之前,审查它的源码, 判断是否安全、是否值得授予"宿主任意代码执行权"。当用户说"这个插件安全吗"、 "能不能装"、"审计/审查这个插件或 preset"、"dsh plugin add"、"帮我看看这个 第三方插件"、或贴出一个插件目录/仓库让评估,都要用它。即便用户没明说"安全"、 只要是在引入外部 DSH 代码,就应先做这次审计。
DeepSeek Harness bundle that routes real sandbox escalation prompts through a dedicated approval reviewer
Conversation-local credential handoff that writes through the DSH credential service without returning the secret to model context.
DeepSeek Harness plugin: a masked password input panel in the Web GUI. The agent calls the password_prompt tool, the browser pops an HTML password panel, and the typed value is returned to the agent — no interactive terminal needed.
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.
Bridges vendor agent SDKs into DeepSeek Harness as selectable LLM providers. Works in any DSH mode; DSH keeps its own prompt, tools, sandbox and approvals.
Strict check: verify code and commands against real checkers instead of reading them — Lean 4 kernel checking with an axiom audit, language type/syntax checks, and static defect rules.
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)
DeepSeek Harness (DSH) host-layer plugin: detects and auto-fixes Windows PowerShell command syntax mistakes — bash constructs, broken line continuations, pasted prompts, CRLF pollution — then executes the corrected command through the host shell seam under the normal sandbox/approval policy