noname-iii/dsh-code-checker
C3A plugin for Deepseek Harness (well it may support other AI agent IDEs but I hadn't test it out yet) that checks for error when AI had finished writing the code.
★ 1+ · noname-iii/dsh-code-checker source on GitHub · this plugin in the registry
noname-iii/dsh-code-checker is a DeepSeek Harness plugin rated C3 — powerful capability combined with sensitive behavior. It patches the dsh runtime, executes system commands, starts a network server, 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 | ×44 src, e.g. cli/exec.ts:2, cli/exec.ts:3 |
| starts a network server | net_server | ×1 src, e.g. simulators/static-server.mjs:30 |
| reads credential-class env vars | token_env | CODE_CHECK_LLM_API_KEY |
Services it injects
agents commands shell tools
Hooks it attaches
agent/turn-stopping approval/request session/disposed session/event
Environment variables it reads
CODE_CHECK_LLM_BASE_URL CODE_CHECK_LLM_API_KEY CODE_CHECK_LLM_MODEL TEMP CODECHECKER_TSC DSH_HARNESS_DIR
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.