Kandy

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Kandy integration that uses Membrane for authenticated API access, with no evidence of hidden, destructive, or unrelated behavior.

Install this only if you intend to connect Kandy through Membrane. Review the Membrane CLI package before installing it globally, authenticate only the intended account, prefer discovered scoped actions, and confirm any POST, PUT, PATCH, or DELETE API requests before letting the agent run them.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The skill description is overly broad: 'Manage data, records, and automate workflows' can match many generic enterprise tasks beyond Kandy-specific communications use cases. In agent-routing contexts, this can cause the skill to be invoked for unrelated requests, increasing the chance of unintended external actions, data access, or user confusion.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal