ClawHub
Back to skill

Security audit

Aws Infra Free

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed AWS CLI helper for read-only inventory and health checks, with one local configuration caveat users should understand.

Install only if you are comfortable letting the agent run AWS CLI read-only queries in your configured account. Prefer commands with --region for one-off checks if you do not want the skill to change your default AWS CLI region, and review query output before sharing it because infrastructure names and account details can be sensitive.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (2)

Intent-Code Divergence

Medium
Confidence
94% confidence
Finding
The skill repeatedly claims to be strictly read-only and to perform no change operations, but it instructs users to run `aws configure set region us-west-2`, which changes the local AWS CLI configuration. This is a documentation-integrity and trust issue: users may rely on the read-only claim and unknowingly alter their active environment, potentially causing later commands to target the wrong region.

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The FAQ again recommends `aws configure set region us-west-2` while the skill markets itself as performing no modifications. Although this does not mutate AWS resources, it does persistently change the operator's local CLI state, which can misroute subsequent AWS operations and undermine user expectations about safety boundaries.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.