Daily security scan
Date · 2026-09-11 (UTC — plugins first indexed that day)
Effective tier · new today
dynamic first · this report2 of 31 new entries take their tier from a dynamic audit conclusion; the rest use the static scan tier. Where a conclusion exists it is authoritative (it may raise or lower the tier).
Static scan · new today
rule heuristics · fallbackTier = scan verdict: critical hit → critical; warning / non-blocking critical → high / medium; none → low. Used only when no dynamic conclusion exists.
Dynamic audit · subset of new today
model reads source · no executionTier = highest finding. Of 31 new entries: 2 with a conclusion, 9 queued, 1 failed (no conclusion), 19 low-risk not queued.
Data file updated 2026-10-29 07:30 (UTC+8); latest conclusion audited 2026-10-20 00:24 (UTC+8)
| Plugin | Effective | Static | Dynamic | Findings C/W/I | Manifest | Indexed |
|---|---|---|---|---|---|---|
| dsh-mcp-lazy Lazy MCP gateway for DSH: one stable proxy tool instead of N tool schemas, servers connect on first use and idle out, metadata cached to disk. | low | low | not queued (low risk) | 0/0/4 | 0/0 | 2026-09-11 00:14 |
| dsh-backup-migrator Plugin environment backup and migration for DSH | medium | medium | queued | 0/1/2 | 0/0 | 2026-09-11 00:14 |
| dsh-skill-recommender Session-profile skill recommender for DSH | medium | medium | queued | 0/1/9 | 0/0 | 2026-09-11 00:14 |
| dsh-aliyun-mcp Alibaba Cloud OpenAPI MCP connection for DSH | low | low | not queued (low risk) | 0/0/6 | 0/0 | 2026-09-11 00:14 |
| dsh-goofish-mcp Xianyu (Goofish) read-only monitoring MCP for DSH | low | low | not queued (low risk) | 0/0/3 | 0/0 | 2026-09-11 00:14 |
| dsh-feishu-mcp Feishu (Lark) OpenAPI MCP connection for DSH | medium | medium | queued | 0/3/10 | 0/0 | 2026-09-11 00:14 |
| dsh-zsxq Knowledge Planet (zsxq) integration for DSH | low | low | not queued (low risk) | 0/0/6 | 0/0 | 2026-09-11 00:14 |
| dsh-plugins Independent DSH plugins: cost metrics + browser_use tool. One pnpm monorepo, independently installable and vendable. | medium | medium | queued | 0/1/11 | 0/0 | 2026-09-11 00:14 |
| dsh-npm NPM registry management for DSH | medium | medium | queued | 0/3/8 | 0/0 | 2026-09-11 00:14 |
| QQ.dsh-qqbot 基于DSH-QQBOT项目的dsh-qqbotGPT优化版本 | low | low | not queued (low risk) | 0/0/0 | 0/0 | 2026-09-11 00:14 |
| dsh-wallpaper-position dsh-dream-skin satellite: per-image wallpaper position (X/Y px) settings row. Vibe-coded. | low | low | not queued (low risk) | 0/0/5 | 0/0 | 2026-09-11 02:13 |
| dsh-whale-tools dsh-whale-widget satellite: replace the whale mascot with any image (auto cutout) + restart button + heartbeat. Vibe-coded. | medium | medium | queued | 0/5/8 | 0/0 | 2026-09-11 02:13 |
| dsh-local-dba A local database-administration (DBA) plugin for [DSH](https://github.com/deepseek-ai/deepseek-harness). It ships as a Cordis plugin bundle that registers a set of `db_*` model-facing tools, letting the agent query, inspect schema, run DDL/DML, back up/restore and analyze slow queries against **MySQL / MariaDB** and **PostgreSQL**. | medium | medium | queued | 0/2/7 | 0/0 | 2026-09-11 02:13 |
| dsh-sakurafrp dsh-mobile satellite: manage the SakuraFrp phone-desktop link from DSH UI (status, gateway toggle, pairing QR, devices, self-heal). Vibe-coded. | lowD↓ | medium | low | 0/9/15 | 0/0 | 2026-09-11 02:13 |
| dsh-imagegen-zhenzhen DSH image-generation plugin with native support for zhenzhen-image style async task gateways (submit + poll), including multi-reference image-to-image. Fork of @dickpy/dsh-imagegen. | low | low | not queued (low risk) | 0/0/1 | 0/0 | 2026-09-11 02:13 |
| dsh-newwindows ⚡ Summary-free context window rollover, model-authored notes, and scoped history lookup plugin for DSH. Inspired by OpenAI Codex. | low | low | not queued (low risk) | 0/0/0 | 0/0 | 2026-09-11 02:13 |
| dsh-provider-headers Per-provider request headers in the DSH Models settings page, with per-conversation ${sessionId} expansion. | low | low | not queued (low risk) | 0/0/1 | 0/0 | 2026-09-11 02:13 |
| dsh-reveal-fix Fix DSH's "reveal in file manager" silently doing nothing on Windows. User-space plugin — survives dsh upgrades, no core files patched. | medium | medium | queued | 0/1/0 | 0/0 | 2026-09-11 02:13 |
| dsh-task-board DSH Web GUI 的任务看板插件：侧边栏入口 + 五列看板，任务经 DSH 会话真实执行，host 端持久化并跨设备实时同步。Task board plugin for the DSH web GUI. | low | low | not queued (low risk) | 0/0/0 | 0/0 | 2026-09-11 02:13 |
| dsh_superpowers Superpowers for the DSH: a dsh plugin that registers the Superpowers skills as a skill catalog and injects the using-superpowers bootstrap into the system prompt. | mediumD | medium | medium | 0/5/13 | 0/0 | 2026-09-11 02:13 |
| dsh-find-plugin Find DSH plugins from inside the agent - live GitHub dsh-plugin topic search + the curated awesome-dsh-plugin list, with token auth, rate-limit resilience and offline fallback. Fork of awesome-dsh-plugin/dsh-find-plugin. | low | low | not queued (low risk) | 0/0/6 | 0/0 | 2026-09-11 04:13 |
| dsh-plugin-desk DSH 插件管家：用人话说明每个插件是做什么的，一键停用/启用（热生效），安全卸载。Settings → Plugins → 插件管家 | low | low | not queued (low risk) | 0/0/4 | 0/0 | 2026-09-11 04:13 |
| dsh-livebench-panel DSH web plugin: a LiveBench tab in the Trajectory view. Run LiveBench evaluations against every model configured in the DSH and read scores in place. | medium | medium | audit failed | 0/3/6 | 0/0 | 2026-09-11 04:13 |
| dsh-plugin-use-images 再dsh里面可以使用图片api | low | low | not queued (low risk) | 0/0/1 | 0/0 | 2026-09-11 04:13 |
| dsh-loomy-connect Use the models that ship with the Loomy desktop app inside DSH — no API key. Also adds a Settings card showing the signed-in account and Loomy credits (permanent + daily gift). | medium | medium | queued | 0/3/16 | 0/0 | 2026-09-11 04:13 |
| dsh-plugin-reasoning-efforts 给 DSH 的第三方中转模型补上「推理等级」选择器 —— 和官方模型在聊天框里的体验完全一致。 | low | low | not queued (low risk) | 0/0/0 | 0/0 | 2026-09-11 04:13 |
| dsh-bg-new DSH 网页界面换背景：侧栏「壁纸」按钮弹出右侧抽屉，支持系统预设/纯色/渐变/图片/视频，滚轮+拖动小图同时管缩放与定位，毛玻璃质感，本地媒体伺服不走云端。DSH web background & wallpaper plugin with drawer UI, glassmorphism and local media serving. | low | low | not queued (low risk) | 0/0/3 | 0/0 | 2026-09-11 04:13 |
| dsh-clipboard-menu Adds a right-click cut/copy/paste/select-all menu to DSH composer inputs. | low | low | not queued (low risk) | 0/0/3 | 0/0 | 2026-09-11 04:13 |
| dsh-research-kit dsh-research-kit 是一个 浏览器侧 DSH 插件：它维护科研资源目录、把工作流和用户参数组装成可编辑 Prompt，并由 DSH 当前会话负责实际发送与执行。 | low | low | not queued (low risk) | 0/0/0 | 0/0 | 2026-09-11 04:13 |
| dsh-plugin-session-delete 删除dsh的会话内容 | low | low | not queued (low risk) | 0/0/0 | 0/0 | 2026-09-11 04:13 |
| ai-memory Personal AI memory semantic layer SDK (Rust + SQLite) — short/mid/long-term memory with hybrid recall | low | low | not queued (low risk) | 0/0/1 | 0/0 | 2026-09-11 04:13 |
Dynamic audit results · new today (2 with a conclusion)
The model reads redacted source context and never executes plugin code. When a dynamic conclusion exists it is authoritative (it may raise or lower the level); otherwise the static tier applies. The audit never writes the exemption list.
The dsh entry point is benign (builtins only, no exec/network); residual risks are a third-party telemetry pixel in the brainstorming companion, an operator-gated shell launcher, and a plaintext session key on remote bin…
- mediumBrainstorming companion pages load a third-party tracking image from primeradiant.com · skills/brainstorming/scripts/server.cjs:248
- lowOpt-in browser launcher runs a URL built from env vars through a shell via cp.exec · skills/brainstorming/scripts/server.cjs:535
- lowSession bearer key travels in cleartext HTTP when the companion is bound to a non-loopback host · skills/brainstorming/scripts/server.cjs:286
Host-side plugin driving the dsh-mobile gateway over loopback; all mutating routes are loopback + desktop gated. Only two low-severity hardening gaps found.
- lowTLS certificate verification disabled for public-authority health probes · lib/index.js:234
- lowLegacy pairing helper leaves a QR image containing a live one-time pairing token on disk · scripts/legacy/dsh-mobile-pair.sh:33
Site-wide effective tiers (dynamic first)
Dynamic conclusions set the tier where they exist; the static scan applies only where there is none. 23,461 in-scope entries (23,118 scanned + 343 pending).
Static scan for reference: low 22,953 · medium 0 · high 163 · critical 0 (dynamic conclusions moved these into the effective tiers above).
Critical-tier plugins (18)
Static heuristics + semantic manifest audit + a model-driven dynamic audit — not a full security audit; no code execution, no dependency resolution. Dynamic tiers come from the model reading source context (highest finding) and never exempt a static finding.
Daily report archive
73 reportsWhat does this daily report cover?
This report covers plugins first indexed by dsh.so on 2026-09-11. For each new plugin it records the name, risk tier, scan verdict, critical/warning/info findings, manifest audit signals, and index time. Plugins that were already in the registry before that date are not included.
How are the risk tiers assigned?
Risk tiers follow the same public model used across the site: four levels — critical / high / medium / low — read from finding counts, most severe first. Critical is reserved for secrets, exfiltration, destructive commands, or mining; a high-severity finding without a critical one reads high; medium (warning-level) findings read medium (needs review); no meaningful findings reads low. Where the model-driven dynamic security audit has a conclusion, that conclusion sets the tier (it can raise or lower it); the static scan tier (vet primary, dsh backstop) applies only when there is no conclusion.
Why is this not a full security audit?
The daily scan is a static heuristic scan plus manifest audit. It does not execute code or resolve dependencies, so it cannot prove that a plugin is safe. Use the report to prioritize inspection, not to replace it.
What does the "Manifest" column mean?
Manifest here is the vet engine's semantic analysis of the plugin's JSON manifest — not the dynamic security audit. It flags declaration-level signals such as install scripts, lifecycle hooks and broad file or network permissions.
Is the static scan the only layer?
No. A second, model-driven dynamic security audit runs on top of it for entries the static scan already flags as needing review: it reads source context without executing plugin code, covers that subset only, and its conclusion is authoritative when there is one — it can raise a verdict or lower it; the static scan tier (vet primary, dsh backstop) applies only when there is no dynamic conclusion. Exemptions stay manual and the script never writes the suppression list. This daily report shows both layers: every new entry is marked with its dynamic state (conclusion / queued / failed / out of the queue because it is low risk), and all conclusions of the day are listed below with their tier, model summary and findings. As of the latest run: 2881 dynamic audit records, 2294 with a model conclusion, 323 stricter than the static verdict, 790 softer.
Source: dsh.so security standards · Maintained by dsh.so · Published