Beszel

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Beszel monitoring helper that stores local operational notes only with user confirmation and shows no hidden or executable behavior.

Install only if you want the agent to keep Beszel monitoring context in ~/beszel/. Review what it plans to save, avoid putting tokens or onboarding credentials in those notes, and keep external alert integrations as explicit user-approved 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 (1)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The skill instructs broad future activation on topics like 'Beszel, monitoring alerts, node health, or agent failures,' which can cause the agent to invoke this skill in conversations that only loosely relate to monitoring. That increases the chance of unintended data collection, unnecessary persistence of operational context, and off-topic autonomous behavior without clear user intent.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal