ClawHub

Cross-Asset Intelligence

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only paid financial-analysis API skill; its main risk is disclosed wallet-based spending, not hidden code or data access.

Install only if you are comfortable letting an agent make paid API calls. Use a dedicated Base wallet with only the USDC you are willing to spend, keep WALLET_SIGNING_KEY out of source control, require confirmation for paid or higher-tier endpoints where possible, and treat all outputs as market research rather than financial advice.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill advertises many broad trigger phrases such as generic requests for market analysis, sentiment, portfolio risk, and trading-related briefings. In an agent environment, this increases the chance of unintended invocation, which is especially risky here because invocation can immediately lead to paid external API calls and financial recommendations from a third party.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill states that the agent's wallet 'pays automatically per request' but presents this as normal setup/usage rather than a prominent spending warning. Because the skill is designed to trigger paid x402 micropayments without an API key, accidental or repeated invocation could silently drain agent funds, especially when combined with the broad trigger language elsewhere in the file.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal