Install verification: sandbox install ok, web smoke failed (L5) · tested on dsh 0.2.1-rc.5 · last checked Install verification details →
Data as of (UTC)
What it doesAI
WeChat floating-ball bridge plugin that logs in via QR code and relays chat messages to your DSH agent.
- QR-code WeChat login flow
- Floating-ball overlay to send and relay messages
- Maintained fork: context_token + login-loop fixes
Capability tags are AI-inferred or rule-extracted from the README (see badge) — vocabulary-limited, not install-verified. AI = inferred; README = literal keyword from the readme.
Trends
Four lines, four questions: total stars, stars gained this week, cumulative downloads, downloads this week. The GitHub pair comes from real-read sampling (a rotating daily shard); the npm pair from every snapshot.
5 samples (roughly every 5 days), 3 of them reconstructed (hollow dots); sampled points, not a daily series
09-22 → 10-22 · 5 points
Each bar = the delta between two samples 5–14 days apart; negative bars point down. Faint bars include reconstructed points
10-02 → 10-22 · 4 points
Reconstructed backwards from the current total using daily downloads (gaps are not interpolated)
09-21 → 10-30 · 38 points
The snapshot’s last-week rolling window (official npm + npmmirror combined)
09-21 → 10-30 · 38 points
Installation
dsh plugin --profile web add dsh-wechat-clawbotInstall method: npm · sandbox install ok, web smoke failed (L5)
Verification & Compatibility
Grouped by plugin version: each card lists the dsh versions actually tested against that artifact version and their install verdicts (L5 wins). Untested combinations are omitted — absence means untested, never assumed compatible. L1–L3 are a plugin-level static archive (independent of the dsh version — the same verdict on every dsh row): they sit in each row's level grid next to L4/L5, marked "static", while their evidence is stored once per plugin inside that row's "checks & evidence" instead of being duplicated per version.
External credentials (plugin-level): none detected
Based on 1 requirement(s) across 3 @deepseek-ai/dsh-* packages. raw ranges
^0.1.0-rc.6 || ^0.1.1-rc.1 || ^0.1.2-alpha.1 || ^0.1.5-rc.1 || ^0.2.0-rc.2 ×3
✓ Running dsh 0.2.1-rc.5 is within the declared range — install is not blocked by version.
Deciding channel: no engines.dsh declared, so every dsh* peer is checked (workspace:^ | ~ | * counts as the running version).
Whether it actually runs is a separate question → see the measured matrix below (L1–L5).
| plugin ＼ dsh | dsh 0.2.1-rc.5 current | dsh 0.2.1-rc.3 | dsh 0.2.1-rc.2 | dsh 0.2.1-alpha.4 | dsh 0.2.1-alpha.2 |
|---|---|---|---|---|---|
| 0.3.1 | ✗ | ✗ | ✗ | ✗ | ✗ |
| 0.3.0 | · | · | · | · | · |
| 0.2.2 | · | · | · | · | · |
| 0.2.1 | · | · | · | · | · |
| 0.2.0 | · | · | · | · | · |
0.3.1npm7 failed2026-10-31
dsh-wechat-clawbot
✗dsh 0.2.1-rc.5current2026-10-31L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.2.1-rc.5
- • Plugin artifact: npm · dsh-wechat-clawbot@0.3.1
ID: dsh-wechat-clawbot@0.3.1@dsh0.2.1-rc.5 · profile: l4-sandbox
Issued: 2026-10-31 · expires: 2026-11-07
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✗dsh 0.2.1-rc.32026-10-26L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.2.1-rc.3
- • Plugin artifact: npm · dsh-wechat-clawbot@0.3.1
ID: dsh-wechat-clawbot@0.3.1@dsh0.2.1-rc.3 · profile: l4-sandbox
Issued: 2026-10-26 · expires: 2026-11-02
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✗dsh 0.2.1-rc.22026-10-19L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.2.1-rc.2
- • Plugin artifact: npm · dsh-wechat-clawbot@0.3.1
ID: dsh-wechat-clawbot@0.3.1@dsh0.2.1-rc.2 · profile: l4-sandbox
Issued: 2026-10-19 · expires: 2026-10-26
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✗dsh 0.2.1-alpha.42026-10-16L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.2.1-alpha.4
- • Plugin artifact: npm · dsh-wechat-clawbot@0.3.1
ID: dsh-wechat-clawbot@0.3.1@dsh0.2.1-alpha.4 · profile: l4-sandbox
Issued: 2026-10-16 · expires: 2026-10-23
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✗dsh 0.2.1-alpha.22026-10-11L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.2.1-alpha.2
- • Plugin artifact: npm · dsh-wechat-clawbot@0.3.1
ID: dsh-wechat-clawbot@0.3.1@dsh0.2.1-alpha.2 · profile: l4-sandbox
Issued: 2026-10-11 · expires: 2026-10-18
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✗dsh 0.2.0-rc.22026-10-08L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.2.0-rc.2
- • Plugin artifact: npm · dsh-wechat-clawbot@0.3.1
ID: dsh-wechat-clawbot@0.3.1@dsh0.2.0-rc.2 · profile: l4-sandbox
Issued: 2026-10-08 · expires: 2026-10-15
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✗prehistory2026-10-05L5 · failed
- • Node.js: v24.14.0
- • DSH: unknown
- • Plugin artifact: npm · dsh-wechat-clawbot@0.3.1
ID: dsh-wechat-clawbot@0.3.1@dshunknown · profile: l4-sandbox
Issued: 2026-10-05 · expires: 2026-10-12
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
0.3.0npm1 failed2026-09-30
dsh-wechat-clawbot
✗dsh 0.2.0-rc.12026-09-30L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.2.0-rc.1
- • Plugin artifact: npm · dsh-wechat-clawbot@0.3.0
ID: dsh-wechat-clawbot@0.3.0@dsh0.2.0-rc.1 · profile: l4-sandbox
Issued: 2026-09-30 · expires: 2026-10-07
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
0.2.2npm3 failed2026-09-26
dsh-wechat-clawbot
✗dsh 0.1.7-rc.22026-09-26L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.1.7-rc.2
- • Plugin artifact: npm · dsh-wechat-clawbot@0.2.2
ID: dsh-wechat-clawbot@0.2.2@dsh0.1.7-rc.2 · profile: l4-sandbox
Issued: 2026-09-26 · expires: 2026-10-03
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✗dsh 0.1.7-rc.12026-09-24L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.1.7-rc.1
- • Plugin artifact: npm · dsh-wechat-clawbot@0.2.2
ID: dsh-wechat-clawbot@0.2.2@dsh0.1.7-rc.1 · profile: l4-sandbox
Issued: 2026-09-24 · expires: 2026-10-01
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✗dsh 0.1.6-alpha.22026-09-20L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.1.6-alpha.2
- • Plugin artifact: npm · dsh-wechat-clawbot@0.2.2
ID: dsh-wechat-clawbot@0.2.2@dsh0.1.6-alpha.2 · profile: l4-sandbox
Issued: 2026-09-20 · expires: 2026-09-27
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
0.2.1npm1 failed2026-09-20
dsh-wechat-clawbot
✗dsh 0.1.6-alpha.22026-09-20L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.1.6-alpha.2
- • Plugin artifact: npm · dsh-wechat-clawbot@0.2.1
ID: dsh-wechat-clawbot@0.2.1@dsh0.1.6-alpha.2 · profile: l4-sandbox
Issued: 2026-09-20 · expires: 2026-09-27
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
0.2.0npm1 failed2026-09-19
dsh-wechat-clawbot
✗dsh 0.1.6-alpha.12026-09-18L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.1.6-alpha.1
- • Plugin artifact: npm · dsh-wechat-clawbot@0.2.0
ID: dsh-wechat-clawbot@0.2.0@dsh0.1.6-alpha.1 · profile: l3-fullscan
Issued: 2026-09-18 · expires: 2026-09-25
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
Only the latest 3 published versions are shown; source-snapshot (commit hash) groups, unstated groups and older versions are omitted — the full archive stays in the data layer (snapshot/unstated groups appear only when a plugin has no published version).
Author badges
Embed the dsh.so badges in your README to show this plugin's automated security-scan and install-test status:
`[](https://www.dsh.so/artifact/dsh-wechat-clawbot/?ref=badge)`dsh.so is an independent community project, not affiliated with or endorsed by DeepSeek AI. Badges are maintained by dsh.so; embed links carry a ?ref= attribution parameter.
Security Report
Two automated layers, neither a manual review: a static scan (per-plugin rule checks) and a model-driven dynamic security audit that covers only the subset static-flagged at warn or above and never executes plugin code.
Static low; dynamic medium (authoritative when present) → overall medium.
v0.3.1dsh manifest0.3.1npm2026-11-010.3.1same versionclean · npmVet is an AST static scan (npm artifact or git source).
show static findings (12)
- warningnetIp · network
dsh-client-wechat-ui/client.js:19var GATEWAY = "http://127.0.0.1:51235"; - warningnetIp · network
dsh-client-wechat-ui/client.js:367var MODEL_API = "http://127.0.0.1:51236"; - warningchildProcess · code-exec
dsh-wechat-bot/index.js:403child = spawn(nodeBin, [entry], { - warningnetIp · network
dsh-wechat-bot/index.js:244const gatewayUrl = `http://127.0.0.1:${config.gatewayPort}` - warningnetIp · network
dsh-wechat-bot/index.js:744logger.info(`dsh-wechat-bot: model endpoint on http://127.0.0.1:${config.modelPort}`) - warningfsWrite · files
dsh-wechat-bot/index.js:261fs.writeFileSync(modelStateFile, JSON.stringify(next, null, 2), 'utf8') - warningfsWrite · files
dsh-wechat-bot/index.js:281fs.writeFileSync(wechatSessionFile, JSON.stringify({ index: wechatSessionIndex }, null, 2), 'utf8') - warningfsWrite · files
dsh-wechat-bot/index.js:467fs.writeFileSync(file, JSON.stringify(value, null, 2), 'utf8') - warningfsWrite · files
dsh-wechat-bridge/index.js:144fs.writeFileSync( - warningnetIp · network
install-dsh-bridge.sh:52echo " 2. 验证: curl http://127.0.0.1:51234/health" - warningnetIp · network
scripts/portability.mjs:410if (listening) pass('验证实例已监听', `http://127.0.0.1:${port}`) - warningnetIp · network
scripts/portability.mjs:446const base = `http://127.0.0.1:${port}`
show 3 audit findings
- mediumModel endpoint sends Access-Control-Allow-Origin: * with no auth or origin check
dsh-wechat-bot/index.js:659The server on 127.0.0.1:51236 answers preflights with ACAO * and allows the Content-Type header, so any web page open in the user's browser can POST /model (and /wechat/new) cross-origin. That persists an arbitrary provider/model/reasoningEffort into ~/.dsh-wechat/clawbot-model.json, which bridge-config injects into every WeChat-driven turn (agent/request hook), and GET /model discloses configured model names and whether an API key exists. No Origin, token or Content-Type validation is performed.
- mediumUnauthenticated loopback bridge accepts cross-site POST /message that drives the DSH agent
dsh-wechat-bridge/index.js:56With the default empty token, authorized() returns true for every request and the handler on 127.0.0.1:51234 (default host 127.0.0.1) parses the body as JSON regardless of Content-Type and validates neither Origin nor Host. A malicious page can therefore send a simple cross-site POST (e.g. text/plain body {"text":"..."}) and have that text injected as a user turn into a live agent session — sessionMode 'active' targets the session the user is looking at. The reply is unreadable cross-origin, so this is blind injection, but the agent still executes the prompt. Reachable only when the user also
- lowWeChat tool approvals are keyed per conversation, so any sender in that chat can approve
dsh-wechat-bot/index.js:335sessionKey is computed as wechat:<index> (line 329), i.e. one key shared by every WeChat sender, and handleMessage performs no check on `from`. claimApprovalReply in dsh-wechat-bridge only matches APPROVAL_ALLOW/APPROVAL_DENY tokens ('1'/'批准' …) against approvals.get(sessionKey).active, so any inbound message that reaches the plugin can grant the pending tool approval for a turn started by the legitimate user. Reachability depends on the gateway allowlist (not harvested); the plugin's own header states an empty allowlist means allow-all.
Two medium risks: a CORS-open local model endpoint ('*') any web page can rewrite, and an unauthenticated loopback bridge letting cross-site POSTs inject prompts into the agent.
Rule (2026-10-28): when a dynamic conclusion exists it is authoritative (it may raise or lower the level); the static scan tier (vet primary, dsh backstop) applies only when there is none (not queued / audit failed / withdrawn). The audit never writes the exemption list (exemptions are manual only); a wrong conclusion is withdrawn by human review and the tier falls back to the static scan tier.
Disclaimer: the static scan and the dynamic security audit are both automated analysis, not a security guarantee. Always review what you install.
Activity
Last commit 2026-09-29 · activity: Stable
• Repo created: 2026-09-17
• Stars: ★ 1 · Forks: 0
• Health: Stable — committed within 90 days
Source
Author README
View on GitHub ↗The author's original README from the repository — fetched live, unedited (the English page loads the default README).
Frequently asked questions
What is dsh-wechat-clawbot?
dsh-wechat-clawbot is a DeepSeek Harness (dsh) plugin listed on dsh.so — an independent community registry that indexes public source repositories and publishes automated security-scan and install-verification results for each entry.
Is dsh.so or this plugin page official?
dsh.so is an independent community registry and is not affiliated with, endorsed by, or sponsored by DeepSeek AI.
How do I install dsh-wechat-clawbot?
Run dsh plugin --profile web add dsh-wechat-clawbot in a DeepSeek Harness (dsh) environment. That exact command passed a real install inside an isolated sandbox (L4); the web smoke test (L5) has not passed yet.
How does the security scan relate to a manual audit?
Both layers are automated, not a manual audit. The static scan is heuristic analysis of the repository source, so it can produce false positives and miss context. The model-driven dynamic security audit only covers plugins static-flagged at warn or above, never executes plugin code, and its conclusion is authoritative when there is one (it may raise or lower the static tier); exemptions stay manual. Neither layer is an endorsement: review the repository and the permissions it asks for before installing, together with the verification level and health signals.
How fresh is the data on this page?
The data on this page is as of 2026-11-01 (UTC) — the most recent valid timestamp among the registry refresh, install verification, security scan and dynamic audit. Build time is never used as a data date.