dsh-api-relay-audit
DeepSeek Harness bundle for running API Relay Audit locally
110 results
DeepSeek Harness bundle for running API Relay Audit locally
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.
Read-only security & compliance toolkit for DeepSeek Harness: prompt-injection detection (rule engine with a pluggable model classifier), Chinese-PII and structured-JSON redaction, and a local configuration security audit that emits redacted, reproducible, self-checksummed risk reports.
🐳 The Everything-Plugin Quant OS — AI-native & DSH-native: 46 tools, 6 pluggable domains (data/alpha/ML/risk/execution), one end-to-end PDAT→PET pipeline. Methods open, secrets internal.
Normalize redundant sandbox requests and malformed justifications in DeepSeek Harness tools
MCP bridge: lets ChatGPT Web create, view, continue and control DeepSeek Harness (DSH) agent sessions through the official MCP protocol. The bridge only connects; DSH keeps its session, agent, tool, approval and workspace security model.
DSH local security audit tool: read-only scans of config, credential metadata, plugin provenance, session structure and network exposure; redacted, reproducible, locatable risk reports
Health checks for DeepSeek Harness: manifest/patch/entry/build/pack/install verification, model-callable plugin_check, profile host-shadowing + manifest-BOM detection, environment diagnostics, supply-chain poison preflight, and broken tool-call-sequence detection (#2334).
See what your AI agent protected: session security receipts, visible data provenance, task boundaries, and tool identity checks for DeepSeek Harness.
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.
Agentic Control Plane for DeepSeek Harness — check every tool call against your policies before it runs, and keep a durable record of what was allowed and why.
Enhanced ACP server for DeepSeek Harness: block-level streaming, usage/stat telemetry (cache hit rate, token speed, input/output tokens, context length, turns, tool timing), model & reasoning-effort switching, and permission-preset control over the ACP wire (Zed-friendly)
DSH sandbox extension: configurable trusted writable roots outside the workspace, for both sandboxed CLI commands and the write/edit tools. 为 DSH 默认沙箱增加可配置的「沙箱授权目录」,允许工作区外的受信修改。
Fail-closed microsandbox microVM provider and model-facing guest tools
Allow, ask, or deny DeepSeek Harness tool calls before execution
Session execution analytics and audit reports for DeepSeek Harness. Understand how your agent actually worked: steps, tool calls, failures, repeated actions, token usage and verification signals.
Approval mode control for DeepSeek Harness: default approval (ask) or bypass approval (auto-approve every tool call), next to the permission selector. DSH 审批模式插件。
DSH tool-call compatibility: strips sandbox_permissions/justification from tool-call arguments for third-party models (GPT etc.), and lets the user skip possibly-stuck tool calls with an LLM-facing notice.
DSH 测试沙盒插件:把开发/测试任务路由到进程级隔离的沙盒实例(独立进程 + 独立 DSH_HOME + 独立端口),提供创建/注入/运行/健康检查/停止/销毁/清理与门禁式合回等原生工具,全程零影响本体(3080)。
DSH context-window relief: knowledge base (ctx_index/search), routing enforcement (deny flood tools), sandboxed execution (ctx_execute/batch Think-in-Code), and session continuity (post-compaction restore).
Model-facing typed tools wrapping the frozen, reviewed underseal adapter for the DeepSeek Harness
Automode for DeepSeek Harness: a fourth permission preset that runs on full access with an LLM classifier as the only gate before every tool call
OMV Audit Desk: an evidence-first vulnerability audit workbench for DeepSeek Harness
DSH WebUI capability controls for skills, MCP servers, tools, prompt injections, approvals, and safety guards at session, project, and global levels.