Agenty

Security checks across malware telemetry and agentic risk

Overview

This appears to be a real Agenty integration, but it gives an agent broad authenticated ability to change or delete Agenty resources without clear confirmation safeguards.

Install only if you want an agent to operate your Agenty account through Membrane. Use the least-privileged Agenty or Membrane connection available, review any proxy request carefully, and require explicit confirmation before update, delete, start, or stop actions.

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 (2)

Vague Triggers

Medium

Confidence: 85% confidence
Finding: The skill description is broad enough to match many generic data-management or automation requests, which can cause the agent to invoke this skill outside clearly intended Agenty-specific contexts. In a skill that exposes external actions, jobs, schedules, record management, and proxy requests, overbroad routing increases the chance of unintended access, side effects, or destructive operations being surfaced without strong relevance checks.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The documented action set includes clearly destructive capabilities such as deleting agents, deleting schedules, stopping jobs, and updating resources, but the skill provides no warning, confirmation, or approval guidance before using them. In an agent-driven workflow, this can lead to accidental or prompt-induced state changes that disrupt scraping jobs, schedules, or stored data.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal