dsh-api-relay-audit
DeepSeek Harness bundle for running API Relay Audit locally
107 results
DeepSeek Harness bundle for running API Relay Audit locally
DSH redteam security research modes and runtime plugins, managed from one settings page: deploy the nine presets, install, update and uninstall the seventeen runtime plugins for the current profile.
Sandbox-first automatic permission policy for DeepSeek Harness
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.
Role-based Codex / Claude Code / ACP subagent providers for the DeepSeek Harness: continuable children, durable session recovery, per-role product permissions, delegation with a permission ceiling, and a declarative role library.
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.
Model-based permission approval (approve-for-me) for DeepSeek Harness: an approval/request answerer backed by a separate reviewer model
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.
Modular AI research/engineering skill pack for DeepSeek Harness — security audit, paper workflows, dev workflow, storage analysis. Installable via dsh plugin add.
Tuning Engines CLI, MCP server, and Python agent runtime adapters for governed model, agent, skill, and MCP workflows. Fine-tune open-source LLMs, run inference, manage datasets/evaluations, and connect LangGraph or Temporal while Tuning Engines handles policy, audit, usage, and token economics.
Fully customizable keyboard shortcuts for the DeepSeek Harness WebUI — macOS-first defaults, 34 pre-registered features across session/view/clipboard/model/permission/system groups, one-click recording to add your own bindings, silent permission cycling with color feedback.
Model-reviewed Auto Approve permission preset for the DeepSeek Harness Web UI
Fail-closed microsandbox microVM provider and model-facing guest tools
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 compatibility plugin that treats redundant non-escalating sandbox permission fields as a no-op
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。
CC-style auto mode for DeepSeek Harness: deterministic deny/allow rules + pre-execute gate + model-agnostic two-stage classifier. Two-state (allow/reject) classifier since 0.8.0. TypeScript rewrite merging dsh-auto-mode v0.4.1 with Nuo-cl/dsh-auto-mode native integration.
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).
QuickJS/WASM-isolated WorkflowEngine for running model-written DeepSeek Harness orchestration with bounded resource controls.
Register models, assist with portraits, and select the Agent model from a secret-free catalog for DeepSeek Harness.
Model-facing typed tools wrapping the frozen, reviewed underseal adapter for the DeepSeek Harness
DeepSeek Harness plugin for SecurStack security scans, policy checks, doctor diagnostics, and JSON CLI results.
Retrieved ≠ injected: CBDC-gated memory for DeepSeek Harness — decides how memory is USED (use/verify/ignore decisions, feedback learning, full audit); local SQLite + FTS5, bounded, no extra model call