audit 75

Verifiable research-report engine for DeepSeek Harness: a content-addressed evidence ledger (claim — snapshot binding, tamper-evident) plus versioned sealed reports where every claim carries a verification verdict and the manifest hash seals the directory

Per-turn skill audit for DeepSeek Harness, plus an in-app skill manager: a native notification and a resident panel showing which skills each turn invoked, an install sheet that adds, replaces and removes skills without leaving the app, and per-skill prov

Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness — a capability seam (ctx.memory service + local SQLite provider + memory tool + frozen snapshot injection), not another memory warehouse

Per-turn skill audit for DeepSeek Harness, plus an in-app skill manager: a native notification and a resident panel showing which skills each turn invoked, an install sheet that adds, replaces and removes skills without leaving the app, and per-skill prov

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

Per-turn skill audit for DeepSeek Harness, plus an in-app skill manager: a native notification and a resident panel showing which skills each turn invoked, an install sheet that adds, replaces and removes skills without leaving the app, and per-skill prov

A read-only mirror for installed DeepSeek Harness plugins: capability inventory with evidence, cross-plugin conflicts, a diff of what changed since the last scan, and an upgrade preflight that tells you which profiles still boot on a newer DSH

Harness-neutral reliability infrastructure for AI coding agents: reversible destructive actions, pre-emission redaction, recovery evidence, and a shared Decision Protocol with optional native adapters.

DSH 原生多平台调研流水线插件：harvest_scout(多平台发现)/harvest_deep_research(深度研报)/harvest_extract(穿透抓取)/harvest_verify(交叉验证)/harvest_audit(可信度审计)。源于自研 omni-scope 方法论，自包含。

Session replay, fork-tree, audit & compare visualization for DeepSeek Harness — time machine for your agent sessions

Discovery + management wrappers around the gh CLI for AI coding agents. Ships as a standard agent skill, an Agent Plugins 1.0 plugin (plugin.json + skills/), and a dsh plugin (dsh.bundle.patch registers the skill at runtime).

🛡️ 给 DeepSeek Harness 插件拍 X 光 —— DSH 插件安全体检与健康检查。静态启发式审计:代码执行、凭据访问、外传端点、混淆、安装脚本、bundle 清单合规,输出 0-100 风险分与裁决。Plugin security & health scanner for DeepSeek Harness: heuristic static audit (code execution, credential access, exfiltration, obfuscation, insta

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 c

Security audit plugin for DeepSeek Harness: static permission profiling and a runtime sentinel for third-party plugins

Audit the DeepSeek Harness plugin list by origin (official vs self-installed): a /plugin-audit command plus a Source tab in Web Settings

Observe-only hash-chained evidence receipts for DeepSeek Harness

Static capability disclosure for DeepSeek Harness plugins: capabilities, injected prompts, install scripts, and provenance, each with file:line evidence. Facts, not a safety verdict.

自然语言查询 + 商业智能报表插件 for DeepSeek Harness：在 dsh-mysql 连接底座之上，提供 Text2SQL 自然语言查库、15+ 图表类型、Dashboard 仪表盘、指标/维度管理、多维分析、自助分析、报表导出、审计日志与数据权限。Natural-language data queries + enterprise BI reports for DeepSeek Harness: Text2SQL, 15+ chart types, dashboards, metric

DSH数据资产编排主包 — 一键串联脱敏→清洗→盘点→封装，32个插件微内核架构，零依赖TypeScript

Native memory for DeepSeek Harness — auditable facts with evidence chains, powered by StateCore

Plugin security review for DeepSeek Harness: dependency advisories, contextual static evidence, a call-time gate for high-risk plugins, and reversible review-gated enforcement.

Plugin insight center — one answer to '哪些值得装': requirement matching (plugin_guide), environment recipes (recipe), health scoring (plugin_rank), static security scanning (plugin_audit), and a single install verdict (plugin_verdict)

One-click health check & score for your DeepSeek Harness plugins. Scan → Score → Fix → Share. PerfScope for dsh.

Harness 事件流审计面板：观察事件类型、分发模式、计数与最近事件，帮助插件作者理解 harness 内部发生了什么

X-ray for your DeepSeek Harness — diagnostics for what's actually loaded, why, and what it costs: per-plugin context-tax attribution, per-request token ledger, skill catalog pricing, dependency cascades.

Ecosystem-wide plugin health audit for DeepSeek Harness: syncs the GitHub dsh-plugin topic into a local catalog, probes npm, static-scans plugin files for security, scores every plugin (maintenance / docs / npm / ecosystem + security veto), keeps score hi

DeepSeek Harness (dsh) approval answerer backed by the agent-governance sidecar — every approval/request is decided by the deny-by-default gate, L0–L4 rules and the organizational audit chain.

Step-0 observation probe for dsh-compaction-audit: logs every compaction/* session event and probes whether shadowedSeqs still resolve to readable events in session.events. Observe-only; never injects, never blocks.

Pre-install supply-chain poison scanner for DeepSeek Harness plugins: AST analysis (NodeSecure JS-X-Ray) + deobfuscation decoder + regex heuristics to catch credential exfiltration, dynamic code execution, obfuscated imports, and install-time scripts.

Transparent, auditable token accounting for DeepSeek Harness: a restart-safe ledger over the durable session log, a CLI that recomputes it from raw logs and diffs the result, and a bill — by workspace, session, model or provider, exportable as CSV or JSON

Compaction quality / hallucination detector: when a conversation span is compacted, check on two axes that key information survived 鈥?FIDELITY (assertions in the summary must be found verbatim in the original leaf events, else flagged as fabricated) and C

Audit an agent harness against the harness-evaluation criteria, with machine-enforced evidence validation.

地理空间数据质量检查插件 — 检测高程精度、拓扑一致性，输出加权质量评分

科研数据溯源审计插件 — 审计血缘完整性、可复现性、FAIR原则，输出溯源报告

地下管线数据质量检查插件 — 检测覆盖率、接边精度、流向合理性，输出质量评分

dsh 插件曝光度诊断与采用率提升 CLI 工具

DSH 探针工具包：卡面合法性、卡契约校验、审计档生成 —— 四个零依赖 CLI ＋ 一个最小宿主插件壳。

Session audit registry and viewer for DeepSeek Harness: an Audit tab in every session, driven by audit artifacts on disk

Declarative tool-call permission control for DeepSeek Harness — allow/deny/ask rules over tools, paths and commands, fail-closed by default, with JSONL audit log.

dsh 插件 · 登录门 + 账号 / 权限 / 配额 / 审计台账（dsh-passwords 的功能已并入）：HTTPS 登录网关与自签证书、用户增删改查（可一并创建工作区）、工作区白名单与归属跟踪、每小时 token 与每日时长配额、沙盒档位下限、上传/git 开关、三本审计台账（登录/访问/操作）、IP 封禁、TOTP 两步验证。

政务办事指南巡检插件 — 检测漏项/语义/逻辑/格式错误，输出合规审计报告，516测试全通过，v3.8.1新城市白名单补全+网办深度枚举配置化+表格下载实质内容豁免

Persistent audit ledger + precise rollback for DeepSeek Harness file-tool edits: capture pre-edit bytes into a content-addressed store per turn, roll back offline via a standalone CLI.

Operator policy and a tamper-evident decision log for DeepSeek Harness. Every tool call judged against your organisation's pack, and written down.

数据资产盘点扫描插件 — 深度元数据扫描+三性检测，输出资产清单

Audit DSH skills automatically: a host-layer tools/post-execute plugin that ships both the skill body and the audit engine, runs the engine after skill files change (write/edit/shell) or after a bulk restore/backup (any tool invoked with mode: restore|bac

DSH plugin for background security audits, secret leakage detection, and command safety

Plugin security inspector for the DeepSeek Harness web GUI: statically audits installed plugins (dangerous API patterns + dependency review), layers an AI (default-model) online audit, and renders a green/yellow/red report panel.

Synthetic CDI (clinical documentation integrity) auditing plugin for DeepSeek Harness — deterministic SOP-rule evaluation tools + bundled (fictional) gold sets, rules, and agent skills.

依赖安全审计：扫描项目依赖的已知漏洞（OSV.dev）并检测过期依赖（npm registry），返回漏洞严重级/修复版本与升级幅度

Runtime security gate for DeepSeek Harness: egress host allowlist, secret redaction in tool results, and an append-only audit log