Security audit

Cloudmigrate

Security checks across malware telemetry and agentic risk

Overview

This cloud migration skill is not clearly scoped for the powerful cloud credentials and infrastructure-changing actions it asks users to enable.

Review carefully before installing. Use only sandbox or least-privilege temporary credentials, provide access for only the cloud provider needed for the current task, inspect all generated IaC and commands before running them, and require explicit confirmation before any apply, deploy, delete, or cost-incurring operation.

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

Medium

Confidence: 94% confidence
Finding: The skill explicitly instructs users to set multiple high-privilege cloud credentials, a Slack webhook, GitHub token, and Vault address, but provides no warning about least-privilege use, secure storage, scope minimization, or the risk of exposing these secrets in shells, logs, or generated artifacts. In the context of a skill that automates multi-cloud deployments, these credentials can enable broad infrastructure changes and data access, so normalizing direct secret handling materially increases the chance of compromise or misuse.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical

Code: suspicious.exposed_secret_literal
Location: SKILL.md:382