ClawHub

Agent identity and reputation registration

Security checks across malware telemetry and agentic risk

Overview

Review recommended because this skill can manage crypto wallets and send blockchain transactions through an external npm MCP server without clear per-transaction confirmation safeguards.

Install only if you trust the external @quantulabs/8004-mcp package and are comfortable letting it manage wallet material. Use testnet first, pin and review the npm package where possible, use a dedicated low-balance wallet, avoid passing unnecessary environment variables, keep passwords and private keys out of chat logs, and require explicit approval before any mainnet, wallet import, transfer, feedback, registration, URI update, or other write operation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The README shows wallet creation, unlocking, feedback submission, and agent registration flows that can trigger signing or on-chain spending, but it does not place a clear, prominent warning near those examples about private key handling, password sensitivity, or the possibility of spending real funds on mainnet. In an agent/MCP context, users may copy commands verbatim or let automation invoke these tools, increasing the chance of unintended transactions or unsafe secret handling.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The intent-mapping table uses broad natural-language triggers like "my wallets" and "switch to mainnet," which can cause an agent to invoke tools based on casual user phrasing without a strong confirmation boundary. In a skill that exposes blockchain state changes and wallet-related operations, this increases the risk of over-eager tool use, especially when paired with adjacent instructions that normalize operational flows for wallet and chain management.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The write-operation flow instructs the agent to initialize/unlock wallet storage, create wallets, and execute write operations, but it does not require an explicit warning or confirmation before actions that can spend funds or alter on-chain state. In this context, the skill directly supports transactions across Solana and EVM networks, so omission of a confirmation step materially raises the chance of unintended fund expenditure, irreversible registrations, transfers, or configuration changes.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal