xmutfyh/dsh-plugin-writing-guard

C2

DeepSeek Harness (DSH) academic writing guard for papers — 论文去AI味 / AI-writing style detection, evidence preservation, journal-fit calibration, manuscript proofreading, writing_audit & automatic check

★ 10+ · xmutfyh/dsh-plugin-writing-guard source on GitHub · this plugin in the registry

xmutfyh/dsh-plugin-writing-guard is a DeepSeek Harness plugin rated C2 — one powerful capability or sensitive behavior. It patches the dsh runtime, gates tool execution.

What it can do

CapabilityFlagEvidence
patches the dsh runtimeruntime_patch./cordis.patch.yml
gates tool executiontool_gatehook: tools/pre-execute

Services it injects

tools

Hooks it attaches

agent/disposed agent/turn-stopping tools/post-execute tools/pre-execute

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.