sliverp/DeepSeek-harness-weixin
C3Weixin ClawBot channel plugin for DeepSeek Harness with QR login and text/image messaging
★ 1+ · sliverp/DeepSeek-harness-weixin source on GitHub · this plugin in the registry
sliverp/DeepSeek-harness-weixin is a DeepSeek Harness plugin rated C3 — powerful capability combined with sensitive behavior. It patches the dsh runtime, decodes base64 payloads, starts a network server, reads credential-class env vars.
What it can do
| Capability | Flag | Evidence |
|---|---|---|
| patches the dsh runtime | runtime_patch | ./cordis.patch.yml |
| decodes base64 payloads | base64_decode | ×2 src, e.g. dist/chunk-CFBWVOH7.js:694, src/protocol.ts:317 |
| starts a network server | net_server | ×2 src, e.g. dist/chunk-CFBWVOH7.js:66, src/control.ts:92 |
| reads credential-class env vars | token_env | DSH_WEIXIN_CREDENTIAL_REF |
Services it injects
agentDefaultModel agentPresets agents approval attachments commands credentials llm permissionPresets sessionPersistence
Hooks it attaches
approval/request
Outbound domains
novac2c.cdn.weixin.qq.com ilinkai.weixin.qq.com
Environment variables it reads
DSH_WEIXIN_CONTROL_SOCKET DSH_WEIXIN_CREDENTIAL_REF
How to read this
Levels measure capability surface and transparency, not maliciousness. A C3 plugin can be entirely legitimate — a desktop shell genuinely needs subprocesses. The point is that you can see this before installing. See the levels explained and how dsh plugins work.
Findings come from static analysis of shipped code; nothing is executed. Think a flag is wrong? Open an issue — every flag cites the file and line it came from.