Red Team

Security checks across malware telemetry and agentic risk

Overview

This skill claims to scan agents for security issues, but its main scan command reports a clean result without performing a real scan.

Review carefully before installing or relying on this skill. It appears incomplete and may create false confidence in an agent's safety; ask the publisher to implement real scan logic, document the repository scanning command, and package or declare all dependencies instead of loading code from outside the skill.

SkillSpector

By NVIDIA

Vulnerability Patterns

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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)

Intent-Code Divergence

Medium

Confidence: 97% confidence
Finding: The 'scan' subcommand presents itself as performing a vulnerability scan but does not execute any analysis and always reports zero issues. This can create a false sense of security, causing users or downstream automation to trust an agent as clean when no scan actually occurred.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal