ximengxiaolan/dsh-vision-bridge
C3Composer-attached images are auto-described by an OpenAI-compatible vision model and handed to text-only models (DeepSeek) as text. ???????????
★ 1+ · ximengxiaolan/dsh-vision-bridge source on GitHub · this plugin in the registry
ximengxiaolan/dsh-vision-bridge is a DeepSeek Harness plugin rated C3 — powerful capability combined with sensitive behavior. It patches the dsh runtime, reads credential-class env vars.
What it can do
| Capability | Flag | Evidence |
|---|---|---|
| patches the dsh runtime | runtime_patch | ./cordis.patch.yml |
| reads credential-class env vars | token_env | VISION_API_KEY |
Services it injects
attachments llm
Hooks it attaches
dispose
Environment variables it reads
VISION_API_KEY VISION_BASE_URL VISION_MODEL VISION_LANG
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.