Back to skill

Security audit

Watadot Aws Ec2

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward AWS EC2 command reference, but it includes powerful commands that can delete instances or change network access if a user runs them.

Install only if you expect the agent to help with AWS EC2 administration. Before running any generated AWS command, verify the AWS account, region, instance IDs, security group IDs, and CIDR ranges, especially for termination and SSH ingress changes.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file includes an irreversible instance termination command that can delete user infrastructure and data. Although the line says "DANGER," it does not provide a concrete warning about irreversibility, scope checking, or the need to confirm target instance IDs before execution.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.