Maestro Api

Security checks across malware telemetry and agentic risk

Overview

The skill has a coherent Maestro API payment purpose, but it asks for wallet signing or private-key access and can spend USDC with limited per-payment controls.

Install only if you are comfortable letting an agent sign wallet messages and purchase Maestro API credits. Use a dedicated low-balance wallet or constrained signer, verify the endpoint, network, payee, asset, and exact USDC amount yourself, and require approval for every 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
91% confidence
Finding
The skill explicitly asks for a `PRIVATE_KEY` or wallet signer to perform SIWX signing and on-chain payment, but it does not present a clear user-facing warning that this is highly sensitive credential material that can authorize transactions and potentially expose funds. In a skill that also instructs the agent to make live HTTP requests and buy credits, requesting direct private key access materially increases the risk of wallet compromise, unintended signing, or unauthorized spending if the skill is misused or the surrounding execution environment is unsafe.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal