41 results
DeepSeek Harness plugin: installs the 'minimal-gitbash' agent preset — the Windows variant of the shipped minimal preset that routes the bash tool through Git for Windows bash (MSYS), with automatic shell discovery and sandbox-aware gating.
Fix and diagnose DeepSeek Harness on native Windows. Official PowerShell, Workspace Write, shortcuts, and legacy preset repair. No WSL.
Plugin Hub for DeepSeek Harness (DSH): a graphical app-store inside the Harness Web UI — browse, search, and one-click install GitHub dsh-plugins, with local ratings, dependency impact graphs, audit logging, and a development scaffold
WebUI-managed encrypted credentials for DeepSeek Harness: one file, plaintext until a password is set, then AES-256-GCM ciphertext under an Argon2id-derived key with SHA3-256 fingerprints; per-request decryption, unlock lockout, leak-guard output redaction, and shipped-code integrity self-checks.
Tensorlake sandbox execution providers for DeepSeek Harness
OrbStack VM sandbox v0.4.0: 在 v0.3(安全/可靠性)基础上新增 A1 交互终端、A3 场景化一键创建、A4 删除撤销+完成通知、A5 配额一眼可见、A6 协作分组、B1 安全基线 vm_harden、B2 密钥库 vm_secret、C1 增强指标+阈值告警 vm_alert、D1 vm_scp/vm_logs/vm_env/vm_withdraw、D2 调度 UI+用量报表 vm_report、D3 导出分片/远端、D4 累计配额+创建排队。
dsh-yolo-mode —— DeepSeek Harness 双面包插件：当会话处于可写沙箱模式且审批策略为 ask 时，用大模型自动裁决沙箱升权申请，支持内置预设与自定义权限层级，并提供宿主 settings + 自发布设置桥（/yolo-mode）与 Web 客户端 UI。
Audit deepseek-harness (DSH) plugins before install, guard them at runtime. Static verdict + pre-install audit protocol; supply-chain checks (typosquat, OSV); exfiltration & ransomware detection, honeypot canaries, integrity baseline. Alarm-only; blocks confirmed destructive ops.
DeepSeek Harness 自动审批插件：在 workspace-write 沙箱之上增加 Auto 档——确定性规则放行/拒绝，模糊操作由 LLM 裁决，危险操作转人工。保留工作区沙箱边界，不放宽为 full-access。
Model-facing typed tools wrapping the frozen, reviewed underseal adapter for the DeepSeek Harness
DSH web plugin: adds a one-click Compact button and a New Session button to the conversation context meter panel. Compact submits /compact to summarize older history; New Session starts a fresh session in the same workspace (agent preset and permission settings follow the deployment default).
AI approval answerer using the unified ctx.llm route with fail-closed local policy checks
DSH WebUI capability controls for skills, MCP servers, tools, prompt injections, approvals, and safety guards at session, project, and global levels.
PRO-LONG-style programmatic memory for DeepSeek Harness: appends every session event to a per-workspace log.txt that the agent retrieves with grep/python. Built-in write probe, /prolong status command and permission-deny counter.
Security review gate for DeepSeek Harness (dsh) plugins: static pre-install vetting of malicious code, vulnerabilities and supply-chain risks (with deobfuscation decoding), runtime audit, optional tool-call guard, and a one-click web review/install/uninstall panel.
Agent-decided approvals for DeepSeek Harness: a workspace-write base permission mode where an independent approval subagent judges every sandbox escalation (risky operations are rejected), with a configurable approval model and a per-session audit trail in the conversation window's 审批 tab.
DeepSeek Harness bundle that routes real sandbox escalation prompts through a dedicated approval reviewer
DSH plugin: auto mode that routes permission-gated tool calls through an LLM review before approving, blocking, or asking for confirmation.
DeepSeek Harness plugin (temporary, pre-upstream-fix): automatically injects a CPython tempfile shim (PYTHONPATH -> sitecustomize) into every confined shell command on the Windows sandbox, so python/pytest tempfile use works with zero extra tools, zero model-context overhead, and zero escalation.
Seatbelt (libsandbox) sandbox provider for the DeepSeek Harness sandbox seam on macOS: a cordis plugin that replaces @deepseek-ai/dsh-sandbox-local's seatbelt rung via a prebuilt seatbelt-run launcher — no dsh source changes, no PR required
Audit an agent harness against the harness-evaluation criteria, with machine-enforced evidence validation.
Forgetting engine for AI agents — memory TTL, decay, eviction, audit. The opposite of memory programming.
DSH Auto Guard: a Claude Code Auto Mode-like command approval mechanism that adds an LLM safety net on top of full access, with rules, caches, file tracker, and sensitive path gates.
dsh plugins ported from eco-agent: permission gate, audit chain, memory tree