x402 (official examples)

Security checks across malware telemetry and agentic risk

Overview

This skill is purpose-aligned payment documentation, but it normalizes giving an agent raw crypto private keys and making paid requests without clear spend limits or approval controls.

Install only if you are comfortable letting the agent work with crypto payment credentials. Use a dedicated low-balance wallet or testnet keys, avoid primary wallets, set spending limits outside the skill where possible, and require explicit confirmation before any paid request.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill instructs users to place raw EVM and Solana private keys in environment variables and then demonstrates code that automatically signs and submits payments to remote resources. In the context of an agent skill, this is dangerous because it normalizes direct secret injection and autonomous fund spending without explicit safety guardrails, spending limits, key isolation, or user confirmation.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal