qiushi-dsh-evidence-audit
Observe-only hash-chained evidence receipts for DeepSeek Harness
417 results
Observe-only hash-chained evidence receipts for 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
Fail-closed microsandbox microVM provider and model-facing guest tools
Content-addressed receipts for skills actually loaded by DeepSeek Harness
DSH 规则执行引擎 v3:容器解析 AGENTS.md + 理解器 + 匹配机 + 执行框架
Allow, ask, or deny DeepSeek Harness tool calls before execution
Run the DeepSeek Harness agent's filesystem, bash and PTY terminals inside a Docker container, so execution state survives a harness restart.
Security-first QQ Bot channel plugin for DeepSeek Harness, built on Tencent's official SDK
DSH plugin: strip GPT-family tool-call sandbox_permissions that are not strictly wider than the current session.
Native memory for DeepSeek Harness — auditable facts with evidence chains, powered by StateCore
Windows Git Bash fix for DeepSeek Harness (dsh): MSYS sandbox conflict + terminal inspector, plus the minimal-win collective-thinking preset (we/let's reasoning chain).
nono (Landlock/Seatbelt) backend for the DeepSeek Harness sandbox seam with a vendored fail-closed executor
QuickJS/WASM-isolated WorkflowEngine for running model-written DeepSeek Harness orchestration with bounded resource controls.
Content-addressed, value-redacted policy drift evidence for DeepSeek Harness
工具调用规范守卫:对 agent 工具调用参数做字符串匹配,命中危险行为拦截并注入原因(deny),或放行但注入警告(warn),附规则管理面板
DeepSeek Companion Enterprise — DeepSeek Harness 企业级伴侣插件:安全审计与 DLP、团队协作与知识管理、任务编排、多模型竞技场、执行轨迹分析、Prompt 工程工作台、API 成本治理。
Local prompt-injection and secret-exfiltration firewall for DeepSeek Harness
Model-facing typed tools wrapping the frozen, reviewed underseal adapter for the DeepSeek Harness
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.
A middle permission tier for DeepSeek Harness between workspace-write and danger-full-access: auto-approves harmless commands and operations targeting configured trusted areas, beyond the current workspace.
DeepSeek Harness plugin for SecurStack security scans, policy checks, doctor diagnostics, and JSON CLI results.
Real-time attention alerts for DeepSeek Harness: a global banner plus flashing workspace entries when the agent is blocked (approval request / sandbox denial), with an audible chime and OS-level notifications for new blockers.
Cybersecurity and reverse-engineering skill router for coding agents (pi / DSH / Codex CLI / Claude Code). Explicitly invoke when reverse-engineering, security analysis, CTF, or pentesting workflow is required.
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.