test

Security checks across malware telemetry and agentic risk

Overview

This is a red-team analysis skill whose sensitive behaviors are disclosed and mostly limited to local customization, local notification, and multi-agent analysis.

Install only if you are comfortable with the skill reading its local customization directory and sending a localhost notification when workflows run. Keep files in the customization directory trusted, avoid giving the workflow secrets or private data you do not want copied into subagent prompts, and review any optional sharing step before using it.

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

Low

Confidence: 92% confidence
Finding: The skill explicitly instructs the agent to issue a background HTTP POST to a local service without user consent, visibility, or safety checks. Even though the destination is localhost, this is still an external transmission from the agent to another process and can leak execution context or trigger unintended behavior in any service bound to that port.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal