BiBoyang/dsh-eval-harness
C3DSH 插件评测工具：YAML 用例驱动真实 agent 回归评测 + baseline 对比 PASS/WARN/FAIL 门禁｜Regression eval harness for DeepSeek Harness plugins
★ 5+ · BiBoyang/dsh-eval-harness source on GitHub · this plugin in the registry
BiBoyang/dsh-eval-harness is a DeepSeek Harness plugin rated C3 — powerful capability combined with sensitive behavior. It patches the dsh runtime, executes system commands, reads credential-class env vars.
What it can do
| Capability | Flag | Evidence |
|---|---|---|
| patches the dsh runtime | runtime_patch | ./cordis.patch.yml |
| executes system commands | exec | ×4 src, e.g. src/runner.ts:1, src/runner.ts:1 |
| reads credential-class env vars | token_env | DEEPSEEK_API_KEY, EVAL_JUDGE_API_KEY |
Services it injects
tools
Outbound domains
api.deepseek.com
Environment variables it reads
EVAL_JUDGE_API_KEY DEEPSEEK_API_KEY EVAL_JUDGE_BASE_URL EVAL_JUDGE_MODEL DSH_BIN
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.