Security audit

CSFloat

Security checks across malware telemetry and agentic risk

Overview

This skill is mostly a simple CSFloat API helper, but it also documents creating live marketplace listings while presenting itself as a read-only lookup tool.

Install only if you are comfortable giving the agent a CSFloat API key and understand that the documented commands include creating listings, not just viewing them. Avoid or remove the create-listing example unless you explicitly intend to post a listing and have checked the asset ID, price, and visibility.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Description-Behavior Mismatch

Medium

Confidence: 97% confidence
Finding: The skill metadata and description say it only queries CSFloat data, but the documentation also includes a POST example that creates a listing. This mismatch can mislead a user or calling agent into performing a state-changing marketplace action when they expect read-only behavior, increasing the risk of unintended listings or financial loss.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill documents a state-changing POST operation to create marketplace listings without any warning, confirmation step, or emphasis that it affects a live account. In the context of a trading/marketplace API, this makes accidental or automated creation of listings more dangerous because it can expose assets for sale or cause unintended financial actions.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.