Windsurf

Security checks across malware telemetry and agentic risk

Overview

This is a non-executable Windsurf IDE guide that describes powerful AI coding features but does not itself run code or hide risky behavior.

Installing this skill is reasonable as a reference guide. When using Windsurf/Cascade itself, prefer Chat mode or scoped @file/@folder context for sensitive work, review diffs and dependency or git changes before accepting them, and be careful with global rules because they can affect future projects.

SkillSpector

By NVIDIA

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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)

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill explicitly encourages an autonomous agent mode that can read/write files and run terminal commands, but it does not include a clear warning that these actions may change source code, install packages, modify git state, or otherwise affect the local system. In a developer-tool skill, that omission is risky because users may treat the guidance as routine usage advice and delegate high-level goals without understanding the side effects of autonomous execution.

VirusTotal

47/47 vendors flagged this skill as clean.

View on VirusTotal