Zilliz Skill

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Zilliz Cloud administration skill with powerful commands, but they match its stated purpose and include basic safeguards.

Install only if you want an agent to help administer Zilliz Cloud. Review commands before approval, especially delete/drop, restore, RBAC, billing, and vector deletion operations, and keep API keys, passwords, and card details in your own terminal rather than chat.

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 README advertises high-impact capabilities such as deleting clusters, dropping collections/databases, modifying RBAC, restoring backups, and querying billing without any warning that these actions can be destructive, costly, or security-sensitive. In an agent-skill context, documentation shapes agent behavior; presenting these operations as routine capabilities without confirmation or safety guidance increases the chance of accidental destructive execution or unauthorized changes.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal