AWS CloudWatch

Security checks across malware telemetry and agentic risk

Overview

This CloudWatch skill appears intended for AWS metric lookup, but its Windows command wrapper and sparse credential guidance create enough risk to require review before installation.

Review the code before installing, especially if running on Windows. Use a narrowly scoped CloudWatch read-only IAM policy, prefer short-lived credentials or an IAM role where possible, avoid pasting AWS secrets into prompts, and do not run the skill with broad AWS or local system privileges.

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: 90% confidence
Finding: The skill explicitly requires long-lived AWS access credentials but provides no guidance on secure handling, least-privilege scoping, storage, or logging avoidance. In an agent setting, this increases the chance that users supply highly privileged secrets insecurely or that the skill is run with overbroad credentials, potentially exposing AWS resources and account data if those credentials are mishandled.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal