KCNyu/clawock
C2AI argues. Code settles. The losses stay on the page. A real HK + US brokerage account run by agents that must debate every call, settled by code the model never touches. Install the same decision wor
★ 10+ · KCNyu/clawock source on GitHub · this plugin in the registry
KCNyu/clawock is a DeepSeek Harness plugin rated C2 — one powerful capability or sensitive behavior. It executes system commands, reads credential-class env vars, installable-looking manifest in fixtures only.
A skill, not an installable plugin — ships SKILL.md with no plugin manifest
What it can do
| Capability | Flag | Evidence |
|---|---|---|
| executes system commands | exec | ×6 in authored code, e.g. site/tools/shoot_dsh_queue.js:31, site/tools/shoot_dsh_queue.js:31 |
| reads credential-class env vars | token_env | NOSTR_PRIVATE_KEY, TAVILY_API_KEY |
| installable-looking manifest in fixtures only | dev_manifest | installable-looking manifest in fixtures only: examples/dsh/packages/clawock-dsh/package.json |
Outbound domains
api.tavily.com njump.me kcnyu.github.io
Environment variables it reads
CHROME_EXE OUT DSH_URL NOSTR_TOOLS_PATH BUNDLE PLAYWRIGHT WIDTH HEIGHT DSF PLAYWRIGHT_CORE
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.