Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Security Defense Line 安全防线
v1.0.0安全防线 - 全方位安全防护与威胁防御系统。 当用户需要以下功能时触发此skill： (1) 智能合约安全审计与漏洞检测 (2) 钱包安全检测与防护 (3) 交易安全验证与风险预警 (4) 钓鱼网站/诈骗检测 (5) 私钥/助记词安全管理 (6) 多签钱包配置与管理 (7) 安全事件响应与应急处理 (8) 安全策...
⭐ 0· 61·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
high confidencePurpose & Capability
Skill advertises comprehensive on-chain security tooling but the package does not declare required binaries (Slither/Mythril/etc.), required environment variables, or platform billing integration; code files expect external analysis tools and payment handling that are not represented in the manifest or SKILL metadata. Several referenced scripts (e.g., security_monitor.py) are mentioned in SKILL.md but are missing from the file manifest.
Instruction Scope
SKILL.md instructs the agent/user to run multiple scripts that perform network actions and call external tools. The documentation references environment variables (TELEGRAM_BOT_TOKEN, TELEGRAM_CHAT_ID) and a SkillPay flow, but the skill does not declare those env vars or clearly limit what data will be sent to external endpoints. The billing flow will send the provided user_id to an external billing service (skillpay.me).
Install Mechanism
There is no install spec (instruction-only at packaging level), which lowers automatic install risk, but the bundle includes many executable Python scripts that expect external third-party binaries. Because nothing is installed automatically, the primary risk is that a user or agent executing the scripts will run subprocesses or network calls not declared in the manifest.
Credentials
The package manifest (_meta.json) declares payment-related env names (SKILLPAY_API_KEY, SKILLPAY_USER_ID) but the code contradicts this: payment.py contains a hard-coded billing API key and does not read SKILLPAY_API_KEY. SKILL.md and example configs reference TELEGRAM_BOT_TOKEN and TELEGRAM_CHAT_ID but the skill does not require or declare them. Hard-coded secrets and undeclared env requirements are disproportionate and confusing.
Persistence & Privilege
The skill is not marked always:true, does not request platform-wide persistence, and does not declare modifications to other skills or agent configurations. Autonomous invocation remains possible (platform default) but is not combined with other high-privilege flags.
What to consider before installing
Do not run these scripts or give this skill real secrets until the developer clarifies and fixes the mismatches. Specific concerns to ask/require before installing: (1) remove the hard-coded BILLING API key from payment.py and use an environment variable as declared in _meta.json, or explain why the hard-coded key is safe; (2) update the manifest to list all required env vars (SKILLPAY_USER_ID, SKILLPAY_API_KEY if used, TELEGRAM_BOT_TOKEN, TELEGRAM_CHAT_ID) and explain what data is sent to external endpoints (skillpay.me and any others); (3) declare required external binaries (slither, mythril, aderyn, etc.) and document fallback behavior if they are missing; (4) provide the missing referenced script(s) (security_monitor.py) or remove references; (5) review and audit all network calls—the billing calls send a user_id to skillpay.me and the package will contact that external service; (6) prefer platform-native billing instead of a third-party API embedded in code; (7) run the code in an isolated sandbox and review logs/network traffic before using on production wallets. These inconsistencies could be sloppy engineering or intentional; treat the package as untrusted until the above are resolved.Like a lobster shell, security has layers — review code before you run it.
latestvk973gsmc4b05xa5q847a7qhrsh83t4mt
License
MIT-0
Free to use, modify, and redistribute. No attribution required.