Xieweikang123/dsh-vision-bridge
C2Give a text-only dsh model eyes: pasted images recognized into text via an OpenAI-compatible vision endpoint.
★ 1+ · Xieweikang123/dsh-vision-bridge source on GitHub · this plugin in the registry
Xieweikang123/dsh-vision-bridge is a DeepSeek Harness plugin rated C2 — one powerful capability or sensitive behavior. It decodes base64 payloads, reads credential-class env vars.
What it can do
| Capability | Flag | Evidence |
|---|---|---|
| decodes base64 payloads | base64_decode | ×1 src, e.g. lib/index.js:57 |
| reads credential-class env vars | token_env | DASHSCOPE_API_KEY, DSH_VISION_API_KEY, VISION_API_KEY, ZHIPUAI_API_KEY |
Outbound domains
open.bigmodel.cn
Environment variables it reads
VISION_API_KEY DSH_VISION_API_KEY ZHIPUAI_API_KEY DASHSCOPE_API_KEY
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.