aa1355721445-lgtm/dsh-image-studio
C2DeepSeek Harness 生图插件:本地参考库 + 关键词 + 图片/文字转三视图,模型按情境自己判断发什么图
★ 10+ · aa1355721445-lgtm/dsh-image-studio source on GitHub · this plugin in the registry
aa1355721445-lgtm/dsh-image-studio is a DeepSeek Harness plugin rated C2 — one powerful capability or sensitive behavior. It patches the dsh runtime, can rewrite the system prompt, command execution in build output only, base64 decoding in build output only.
Installable plugin — declares a dsh.bundle manifest
What it can do
| Capability | Flag | Evidence |
|---|---|---|
| patches the dsh runtime | runtime_patch | ./cordis.patch.yml |
| can rewrite the system prompt | prompt_surface | systemPrompt, webServer |
| command execution in build output only | exec_bundled | ×3 in build output only, e.g. lib/http.js:6, lib/http.js:86 |
| base64 decoding in build output only | base64_decode_bundled | ×4 in build output only, e.g. lib/http.js:121, lib/providers.js:107 |
Tool registrations
1 static tool registration point(s).
lib/index.js:111tools.register
Services it injects
slots systemPrompt tools webServer
Outbound domains
api2-cn.65535.space api2.65535.space task-api-1-cn.65535.space task-api-1.65535.space
Environment variables it reads
DSH_HOME USERPROFILE
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.