ClawHub
Back to skill

Security audit

AgentMailer Security

Security checks for vulnerabilities and agentic risk

Overview

This skill is an advisory AgentMailer security guide and does not add execution, data access, or mutation behavior.

This appears appropriate to install as a security-review aid. Users should still treat it as guidance, not as proof an AgentMailer integration is production-safe, and should separately review any linked example code before adopting it.

SkillSpector

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

Static analysis

No suspicious patterns detected.