ClawHub
Back to skill

Security audit

AWS SES

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent AWS SES setup skill with expected AWS account access and email-sending utilities, but users should handle generated SMTP credentials carefully.

Install only if you intend to let your agent help operate AWS SES. Use least-privilege AWS credentials, prefer dry-run before setup or sending commands, and avoid running the SMTP password generator in shared terminals, CI logs, or transcripts because it prints a usable derived SMTP password.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill declares no permissions while instructing use of environment credentials and local shell-capable tooling such as Python scripts and `dig`. This creates a trust-boundary problem: an agent or user may load the skill assuming it is passive documentation, when it actually expects access to secrets and command execution, increasing the chance of unintended credential exposure or command execution without proper review.

Tp4

High
Category
MCP Tool Poisoning
Confidence
80% confidence
Finding
The documented behavior expands beyond the declared purpose by including live email sending, retrieval of suppression and reputation data, CloudWatch metric access, and local subprocess-based DNS inspection. When a skill understates these actions, operators may authorize it in contexts where they did not intend outbound email, account telemetry access, or shell execution, which can lead to misuse of AWS resources and exposure of operational data.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The script prints a valid SES SMTP password derived from an IAM secret directly to stdout, which can expose usable credentials through terminal history, CI/CD logs, shell capture, or shared session transcripts. In this skill context, the output is specifically intended for operational use, so the credential is real and immediately actionable even though it is derived rather than the raw IAM secret.

Static analysis

No suspicious patterns detected.