ClawHub
Back to skill

Security audit

AWS图代理

Security checks across malware telemetry and agentic risk

Overview

This is a coherent AWS deployment guide, but it asks an agent to use AWS credentials and includes cloud resource deployment and deletion commands without enough scoping or safety guidance.

Review this before installing if the agent will be allowed to run commands. Use least-privilege or temporary AWS credentials, avoid placing secrets in prompts or source files, verify the AWS account and region before deployment, and treat `agentcore destroy` as a destructive cloud-resource deletion command requiring explicit confirmation.

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 (2)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill includes a destructive cleanup command (`agentcore destroy`) but does not warn users that it can delete deployed resources and potentially cause service interruption or data loss. In an AI-agent context where commands may be executed on behalf of a user, omission of an explicit deletion warning increases the chance of accidental destructive actions.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill requests AWS access keys and region configuration but provides no warning on secure credential handling. This is dangerous because users or automated agents may place long-lived secrets in insecure locations, logs, prompts, or source-controlled files, leading to compromise of the AWS account used for deployment.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.