Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Coinw Spot Skill
v1.0.3Coinw Spot REST API skill: covers market data, order placement/cancellation, order queries, account balances, and asset transfers.
⭐ 1· 53·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
Name/description, documentation files, and required env vars (COINW_API_KEY, COINW_SECRET_KEY) align with a CoinW spot trading/data integration. The requested environment variables are exactly what a REST trading skill needs. Minor metadata inconsistency: SKILL.md metadata version (1.2.0) differs from registry version (1.0.3) and primaryEnv is not set even though env vars are declared.
Instruction Scope
SKILL.md is instruction-only and stays within API interaction scope (endpoints, signing with secret, query/POST patterns). It instructs users that API keys may be provided in-chat and states the agent will 'mask' and store secrets in OpenClaw credential storage — this requires trusting the platform's secret storage and the skill's claim. The instructions do not ask the agent to read unrelated files or system state.
Install Mechanism
Instruction-only skill with no install spec or code files to run — lowest install risk. Files are documentation only (README and references).
Credentials
Only COINW_API_KEY and COINW_SECRET_KEY are required, which is proportionate for trading. However: (1) the skill suggests users may paste secrets into chat (risk of leakage if chat transparency/permissions are unclear); (2) there's no guidance in the skill about least-privilege API key configuration (e.g., disabling withdrawal or enabling IP whitelist) aside from reference docs — you should create keys with minimal permissions and IP whitelists where possible.
Persistence & Privilege
The skill is marked always: true, which forces it to be included in every agent run. Always:true is an elevated privilege for a trading skill and is rarely necessary; combined with automatic invocation capability it increases the blast radius if the skill or credentials are abused. The SKILL.md's claim about storing credentials in platform storage creates an additional trust requirement — verify how OpenClaw stores and protects secrets before proceeding.
What to consider before installing
This skill appears to be a straightforward CoinW API wrapper, but exercise caution before enabling it:
- Do not paste full API secret keys into chat unless you fully trust the skill source and platform secret storage; prefer setting COINW_API_KEY and COINW_SECRET_KEY as environment variables or using the platform's secure credential UI.
- Create API keys with the minimum required permissions (ideally read-only for data, enable trading only if you need it), disable withdrawals, and enable IP whitelisting and 2FA when available.
- The skill is marked always: true (force-included). Ask why it needs to be always-enabled; if not required, decline or disable that flag to reduce risk.
- Verify the skill's source repository and publisher (registry shows an owner ID but no homepage). If you cannot confirm the publisher or repository authenticity, do not install the skill with real credentials.
- Check OpenClaw's documentation for how credentials are stored and who/what can access them. Consider testing with a low-privilege or sandbox account first.
If you can confirm the author/source is trusted and you follow least-privilege practices, the technical footprint matches the stated purpose; otherwise treat installation as risky.Like a lobster shell, security has layers — review code before you run it.
latestvk973mvtf7nx4rrpgkexgdxfdkh84307s
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
EnvCOINW_API_KEY, COINW_SECRET_KEY