dsh-strip-sandbox-permissions
Strip sandbox_permissions / justification from model tool-call arguments so sandbox escalation is never triggered when the session already has sufficient permission.
70 results
Strip sandbox_permissions / justification from model tool-call arguments so sandbox escalation is never triggered when the session already has sufficient permission.
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)
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).
Out-of-tree DeepSeek Harness bundle: an executable implementation of the Harness Engineering Methodology (HARNESS-METHODOLOGY-SPEC v1.0) — agent-discipline prompt section + artifact scaffolding tool + compliance audit tool.
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.
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)
Hawkeye Scan Workbench - AI-driven source-code security scanning for DeepSeek Harness (DSH): 5 model tools + /hawkeye web UI + JSON/Markdown/HTML vuln reports. Zero-dependency Cordis plugin.
Free security audit for Linux servers — no API keys, no paid tools. Scans for viruses (ClamAV), rootkits (rkhunter + chkrootkit), SSH brute force, crypto miners, exposed credentials, and open ports. 1
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.
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
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.
X-ray for your DeepSeek Harness — diagnostics for what's actually loaded, why, and what it costs: per-plugin context-tax attribution, per-request token ledger, skill catalog pricing, dependency cascades.
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/)
Scan installed DeepSeek Harness plugins and grade stability risk (hook surface, startup work, preflight health, packaging, dependencies). 扫描已安装插件的稳定性风险(钩子面/启动任务/预检/打包/依赖)。
DSH 插件安全审查:静态扫描 + 当前会话模型语义审查 + 用户确认
One-click health check & score for your DeepSeek Harness plugins. Scan → Score → Fix → Share. PerfScope for dsh.
Secret-scrubbing guard plugin: irreversible regex redaction of secrets before session-log persistence and model requests
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
Offline-first static admission scanner for DeepSeek Harness plugins.
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.
V0 capability-disclosure scanner for DeepSeek Harness (DSH) cordis plugins: reports which sensitive services (credentials/shell/approval/sandbox/fs/tools...) a plugin declares or references before you trust it.
Secret & dangerous-pattern scanner for DeepSeek Harness — a security_scan tool that finds leaked API keys, tokens, private keys and credential files, with full redaction.