jing-hy/picturereader

C3

DSH plugin: pixel-to-text image reading for text-only models. image_scan/image_ocr/image_sample tools + image-reading skill (34-image trained methodology). Pure local, optional PaddleOCR.

★ 10+ · jing-hy/picturereader source on GitHub · this plugin in the registry

jing-hy/picturereader is a DeepSeek Harness plugin rated C3 — powerful capability combined with sensitive behavior. It patches the dsh runtime, can rewrite the system prompt, executes system commands, decodes base64 payloads.

Installable plugin — declares a dsh.bundle manifest

What it can do

CapabilityFlagEvidence
patches the dsh runtimeruntime_patch./cordis.patch.yml
can rewrite the system promptprompt_surfacesystem-prompt/assemble
executes system commandsexec×38 in authored code, e.g. scripts/setup-doc-venv.mjs:20, scripts/setup-doc-venv.mjs:20
decodes base64 payloadsbase64_decode×2 in authored code, e.g. scripts/setup-macos.mjs:57, src/core.js:1236
reads credential-class env varstoken_envGLM_API_KEY, SEE_API_KEY

Services it injects

attachments fs llm locale slots tools

Hooks it attaches

llm/adapters-updated llm/stream system-prompt/assemble tools/post-execute

Outbound domains

pypi.tuna.tsinghua.edu.cn api.openai.com open.bigmodel.cn registry.npmmirror.com

Environment variables it reads

DSH_MACOS_OCR_BIN DSH_HOME SEE_API_KEY GLM_API_KEY PICTUREREADER_INSTALL_DIR DSH_RAPID_BASE_PYTHON DSH_PADDLE_PYTHON DSH_PADDLE_CACHE DSH_RAPID_PYTHON DSH_DOC_PYTHON

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.