Microcks

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Microcks integration, but it gives an agent broad authenticated API access that can change or delete Microcks resources without clear confirmation guardrails.

Install only if you trust Membrane and the connected Microcks account scope. Use a least-privileged Microcks/Membrane connection, avoid production-admin credentials where possible, and require explicit approval before any request that creates, updates, or deletes data.

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 documents a generic proxy request capability that can send arbitrary HTTP methods, headers, query parameters, and bodies to the connected Microcks API, including destructive methods like DELETE, POST, PUT, and PATCH. Without an explicit user-facing warning or confirmation requirement, an agent could transmit sensitive data or perform state-changing operations on behalf of the user without adequate awareness or consent.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal