DDDFXYqiming/Agent_Extensions

C3

Agent Skills & DeepSeek Harness (DSH) 扩展库:通用智能体技能(General_skills)+ DSH 标准插件(dsh-plugin),开箱即用的 AI Agent 能力增强集合。

★ 5+ · DDDFXYqiming/Agent_Extensions source on GitHub · this plugin in the registry

DDDFXYqiming/Agent_Extensions 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, reads credential-class env vars.

What it can do

CapabilityFlagEvidence
patches the dsh runtimeruntime_patch./cordis.patch.yml
can rewrite the system promptprompt_surfacesystemPrompt, webServer
executes system commandsexec×12 src, e.g. dsh-plugins/dsh-layered-memory/lib/index.js:29, dsh-plugins/dsh-layered-memory/lib/index.js:29
reads credential-class env varstoken_envVISION_API_KEY

Services it injects

agents conversation credentials sessionQuery sessions skills systemPrompt tools webServer workspaces

Hooks it attaches

agent/disposed session/event tools/result

Outbound domains

api.minimaxi.com

Environment variables it reads

WSL_DISTRO_NAME PYTHON OCR_SERVER_PATH OCR_MODEL_DIR DSH_HOME OCR_EMBEDDING_SERVER_PATH OCR_EMBEDDING_MODEL_DIR COMPARE_TIMEOUT_MS COMPARE_WITH_EMBEDDING OCR_PORT

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.