Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Smart Money
v1.0.2Smart money whale tracking skill. Activate when user mentions smart money, whale tracking, 聪明钱, 鲸鱼追踪, fund tracking, on-chain signals, what are whales buying...
⭐ 0· 68·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Suspicious
medium confidencePurpose & Capability
Name/description align with the included tools and data files (watchlist, labels, signal/watch/list/custom/scan). Using a remote MCP service to compute signals is a plausible design for this skill. The need to persist an agent_id/api_key and to store per-agent monitor state locally is consistent with a remote multi-tenant tracking service.
Instruction Scope
Runtime instructions tell the agent to register with a remote MCP endpoint, persist agent_id/api_key to ~/.smart-money/agent.json, write/read monitor config/state files under ~/.smart-money/, and create cron/scheduled tasks to run scans periodically. Crucially, adding private addresses via smart-money-custom implies sending those addresses to the remote server for scanning; there is no privacy/retention statement in the package. These behaviors go beyond mere read-only lookups and introduce privacy/exfiltration risk if the remote service is untrusted.
Install Mechanism
Instruction-only skill with no install spec, no code files that run locally, and no downloads. This minimizes local code execution risk; the main action is network calls to the declared MCP endpoint.
Credentials
The skill declares no required environment variables, which is coherent, but it instructs the agent to persist and reuse an api_key returned by the remote antalpha-register tool. That api_key and any private addresses you add will be transmitted to and stored on the remote MCP server. There is no documentation in the package about what the api_key authorizes, its lifetime, access controls, or data retention — this is disproportionate to the transparency provided and increases trust/privacy risk.
Persistence & Privilege
The skill does not set always:true, but it explicitly asks the agent to create cron jobs or to check monitor-config on every session, and to persist monitor state and api_key to the user's home directory. That gives the skill practical persistence (periodic autonomous scans and alerts). This is plausible for a monitoring skill but requires user consent and trust in the remote service.
What to consider before installing
This skill uses a remote MCP server (https://mcp-skills.ai.antalpha.com/mcp) to perform scans and requires you to register and persist an api_key and agent_id locally. If you add private wallet addresses they will be sent to that remote service for scanning and storage. Before installing, verify the operator/website and privacy/security policies for the MCP endpoint; do not add private keys or other secrets (only public addresses you consent to share); consider whether you are comfortable the remote service can access/watch the addresses you add; and be cautious about enabling cron/scheduled monitoring because it creates persistent, recurring network activity. If you need stronger assurances, ask the publisher for documentation on api_key scope, data retention, and multi-tenant isolation or prefer a local-only solution that queries public block explorers without transmitting private watchlists to a third party.Like a lobster shell, security has layers — review code before you run it.
latestvk97e2mxsxxht897vacdsg1bxwx84nwxc
License
MIT-0
Free to use, modify, and redistribute. No attribution required.