ClawHub

paynode-402

Security checks across malware telemetry and agentic risk

Overview

This skill openly enables paid external API access with a burner wallet and requires approval before spending, but users should treat it as financially sensitive.

Install only if you are comfortable giving an agent access to a minimally funded burner wallet for paid API calls. Review the API, price, and network before approving any spend, prefer testnet for setup, and pin or locally audit the external CLI before using real funds.

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)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The top-level description says to use this skill whenever built-in knowledge is insufficient, which is an extremely broad trigger for a tool that performs external network access and can spend USDC. That guidance can cause unnecessary activation in ordinary tasks and increases the chance of unintended outbound requests or paid operations without a tightly scoped need.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger section promotes a discovery-first workflow and instructs the agent to check the marketplace before admitting lack of capability. In this skill's context, discovery is itself an external mainnet-oriented action and may normalize unnecessary outbound access for many routine prompts.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The cold-start section says the first action must be outbound marketplace indexing, but it does not lead with a user-facing warning that this is external network activity with potential mainnet/payment sensitivity. For a payment-enabled skill, mandatory discovery without upfront consent materially increases risk of privacy leakage, surprise connectivity, and accidental progression toward paid execution.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal