Hive Mcp Skill
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed connector to Hive's crypto data service through UXC, with no evidence of hidden, destructive, credential-stealing, or broad local-access behavior.
Install this only if you trust your UXC installation and are comfortable sending crypto market queries, wallet addresses, or portfolio lookup inputs to Hive's remote MCP service. Use the documented schema-inspection step before invoking endpoints, and require separate review before any endpoint that could write to an account or change data.
SkillSpector
By NVIDIA
Vulnerability Patterns
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
63/63 vendors flagged this skill as clean.
