audit 65

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

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

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

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

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

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

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

Observe-only hash-chained evidence receipts for DeepSeek Harness

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

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

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)

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

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

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

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.

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

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

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

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.

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

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.

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

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.

Prompt audit for dsh: record a content-addressed digest of every assembled model request — per message (role, id, content hash, author) plus the effective system prompt's identity and hash — to a sidecar file outside the session log. Answers "was this tex

Read-only health auditor for DSH plugins — admission checks plus static security scan, with a 建议安装/谨慎安装/不建议安装 verdict. Never executes the code it audits.

DeepSeek Harness out-of-tree plugin: a file panel beside the conversation — the session's workspace as a tree, the files it produced pinned above, and a mark on every row it touched.

PII detection & exfiltration guard for DeepSeek Harness — scans tool arguments and results for personal data (emails, phone numbers, CN IDs, cards, keys), blocks outbound calls carrying PII, JSONL audit without storing raw matches.

Verification toolkit for DeepSeek Harness agents: evidence-based claim checking against workspace files with line citations, config validation (JSON/YAML), HTTP URL status checks, npm package checks, GitHub repo submission-readiness checks, and batch veri

Installation safety gate & data-protection guard for DeepSeek Harness: 60 static signature rules scan plugin sources for malicious install scripts, credential theft, obfuscation and network callbacks before 'dsh plugin add', with scan baselines (gate_diff

Enterprise compliance for DeepSeek Harness — SOC2/GDPR automated checks, sensitive-info redaction, and a redacted tool audit trail. · DSH 企业级合规插件：SOC2/GDPR 自动化合规自检、敏感信息拦截与脱敏、操作日志审计追溯。

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.

Agent governance suite for DeepSeek Harness (enterprise companion): policy-based tool gating (allow/deny/ask), structured JSONL audit trail, and per-agent token quotas against the host token meter — state under $DSH_HOME/gov

DSH 插件推荐助手：首次使用自动弹出对话框询问你的职业/角色（程序员、设计师、写作、研究、运维、学生…），按角色推荐合适的 DSH 插件，并对每个插件做安全审计（静态扫描）与口碑检查（下载量/星数）。A role-based plugin recommender with security & trust audit for DeepSeek Harness.

Scan installed DeepSeek Harness plugins and grade stability risk (hook surface, startup work, preflight health, packaging, dependencies). 扫描已安装插件的稳定性风险（钩子面/启动任务/预检/打包/依赖）。

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

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，487测试全通过，整改默认内置+热线白名单口径B(去区号匹配)

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。

City data AI classification plugin: auto-recommend GB/T 47949-2026 category and sensitivity grading

Attestation-level data quality report plugin with evidence chain hash and attestation statement

Data asset inventory scan plugin: deep metadata scan + triple condition screening + ownership clue annotation Also known as @deepseek-ai/dsh-data-asset-inventory-scan.

Registration helper plugin: disallowed scenario check + ownership dispute check + agency matching + registration workflow guidance Also known as @deepseek-ai/dsh-data-asset-registration-helper.

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.

Data circulation assessor plugin: trusted data space readiness and transaction compliance prediction