Kintent

Security checks across malware telemetry and agentic risk

Overview

This Kintent skill appears legitimate, but it gives an agent broad authenticated ability to change compliance data without explicit confirmation guardrails.

Install only if you trust Membrane and intend to let an agent work with Kintent compliance data. Use a least-privileged Kintent account, prefer discovered Membrane actions over raw proxy calls, and require explicit confirmation before any create, update, patch, delete, or automation request. Static scan was clean and VirusTotal was still pending, so the Review verdict is based on the artifact’s broad mutable API authority and missing guardrails, not malware evidence.

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: 94% confidence
Finding: The skill explicitly documents a generic proxy request capability with support for mutating HTTP methods like POST, PUT, PATCH, and DELETE, but does not require confirmation before state-changing operations. In a compliance platform context, this can enable unintended modification or deletion of sensitive governance data if an agent translates a vague user request into a direct API call.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal