@dsh-external/dsh-llm-approver
LLM pre-review for sandbox-escalation approvals: an independent-context LLM gate answers sandbox escalation requests before they reach the user, falling back to the user on any failure.
98 results
LLM pre-review for sandbox-escalation approvals: an independent-context LLM gate answers sandbox escalation requests before they reach the user, falling back to the user on any failure.
Sessionless LLM sandbox approval reviewer for DeepSeek Harness.
AI response quality review for DeepSeek Harness: audits each finished assistant turn with an independent reviewer model and steers the agent to fix unreasonable output (up to 2 review rounds).
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.
WeCom (Enterprise WeChat) Smart Robot bridge for DeepSeek Harness — two-way chat over the aibot WebSocket gateway (bot_id + secret), no public endpoint needed.
Authentication and security hardening plugin for DeepSeek Harness
Portable DSH WebUI skill security inspection with local rules and optional model review
Turn DeepSeek Harness sessions into redacted, README-ready animated demos — as a local CLI or DSH plugin.
LLM auto-review approval answerer for DeepSeek Harness — decides sandbox escalations without a human prompt via a deterministic filter and a clean-context LLM safety review. REQUIRES a patched harness core (see core-patches/)
Press Enter to approve the sandbox permission-escalation prompt in the DeepSeek Harness WebUI instead of clicking the Allow once button.
dsh web 认证插件:登录保护、空闲自动登出、认证有效期、设置界面、`dsh web p` 重置密码
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 高级安全认证网关:支持 Argon2id 密码、CSRF 保护、账户锁定、IP 访问控制、审计日志、会话管理、TOTP 两步验证及 WebAuthn/通行密钥预备。零配置启动,即装即用。
DSH 权限预设 workspace-write++:工作区内写文件,可在设置里配置放行 Git Bash / PowerShell 等进程沙箱(修复 Windows ACL 下 MSYS 内存映射错误)。
Configurable auto-approval for DeepSeek Harness: intercepts approval/request and answers allowed-once/rejected by policy (allow-all / allowlist / deny-always), with a full audit log — so the human is only asked when the policy says so.
A DeepSeek Harness Web plugin for inspecting redacted LLM HTTP request and response traces.
Codex-inspired managed approval for DeepSeek Harness: risk-based MCP review, one-time grants, explicit denials, and human fallback on reviewer failure.
Password + CIDR gate for DeepSeek Harness web / DeepSeek Harness 局域网密码门禁
Guard DeepSeek Harness PowerShell, file, image, and search tools on Windows with workspace, credential, approval, and audit policy.
SuperPowers for the DeepSeek Harness: portable Superpowers skills, automatic bootstrap, and DSH-native Windows sandbox compatibility.
Corner approval popup: answer pending permission requests from any session while the agent window is away
Feishu (Lark) OAuth login gate for the DeepSeek Harness web GUI.
Plugin security inspector for the DeepSeek Harness web GUI: statically audits installed plugins (dangerous API patterns + dependency review), layers an AI (default-model) online audit, and renders a green/yellow/red report panel.
DSH compatibility guard: repairs compaction limits, fail-safe sandbox escalation, and missing tool descriptions for third-party models; capability lookups are cached and the deprecated prompt-injection path is off by default.