413 results
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
Security, Trust & Policy Layer for DeepSeek Harness. Don't trust your agent's tools. Verify them.
Self-protection guardrails for the DeepSeek Harness: protected-path interception, backup-before-destroy, CLI self-recovery commands, and strict sandbox defaulting
【实验性】只读安全审计模式插件（自动只读、工具级白名单、强制交付选择）· EXPERIMENTAL plugin for the read-only security audit mode (auto read-only, tool allowlist gate, mandatory delivery choice)；日常使用推荐 dsh-presets 仓库的原生纯预设版。
A fail-closed, auditable approval policy plugin for DeepSeek Harness
DSH-Plugin: structural observability layer — real tool/skill usage recording (tools/result), skill-catalog audit, and a watchdog with health/error events. No model self-reporting.
Enterprise-grade Zero-Trust Authentication, LAN/Public Access Control & Security Gate Plugin for DeepSeek Harness (DSH).
Read-side SIEM forwarder for DeepSeek Harness: normalises session activity to OCSF and ships it
Approval timeout for DeepSeek Harness: when a sandbox/escalation approval is not answered within a configurable period, the request is automatically rejected instead of waiting forever.
Dependency-installation guard for DeepSeek Harness: classifies package-manager commands as ALLOW, ASK, or BLOCK before execution.
AI代码审查：找出代码中的bug、安全漏洞、性能问题和风格建议
Project DeepSeek Harness tool, approval, and result facts into a bounded action lifecycle ledger.
Config drift detective for DSH: snapshots profile/plugin state on startup, records diffs, exposes a read-only history tool. Zero runtime deps, no custom events.
DeepSeek Harness 的 Tailscale 远程访问运营面板：健康检查、HTTPS 入口开关、macOS 代理绕过、中继服务器运维、ACL 片段生成。
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.
Disk-usage audit for DeepSeek Harness (dsh) data directories: total size, per-directory breakdown, largest files, and oversized-file warnings (session logs can hit hundreds of MB). Zero runtime dependencies, read-only. CLI + agent-callable disk_audit tool.
A security-conscious registry and installer for external CLI tools exposed through DeepSeek Harness.
Stavros RedTeam for DeepSeek Harness (DSH) — authorized red-team persona + scope-guarded pentest tooling (persona, 24 subagents, methodology and 78 zero-dependency guard tools).
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.
AgentENV execution-world bundle for DeepSeek Harness
DSH profile plugin: unconfined (GPU-capable) session sandbox plus per-operation user approval for writes outside the workspace or to protected files.
Content-addressed proof for body-free DSH tool-result custody stages
Fail-closed MCP tool baseline and runtime approval security for DeepSeek Harness.
Strip sandbox_permissions / justification from model tool-call arguments so sandbox escalation is never triggered when the session already has sufficient permission.