Aavegotchi Traits

Security checks across malware telemetry and agentic risk

Overview

This is a read-only Aavegotchi lookup skill whose network and environment-variable use fits its stated purpose.

Install only if you are comfortable running a local Node script and installing its npm dependencies. Gotchi names or IDs will be sent to the public Base RPC and Goldsky subgraph, or to any custom RPC/subgraph URL you configure; do not provide wallet private keys or seed phrases.

SkillSpector

By NVIDIA

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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 (1)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 93% confidence
Finding: The skill documentation indicates use of environment variables and outbound network access, but the skill declares no permissions. This creates a permission/transparency gap: users or hosting platforms may not realize the skill can read configuration from the environment and contact external RPC/subgraph endpoints, which can lead to unintended data exposure or unauthorized network access in sensitive agent runtimes.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal