ClawHub
Back to skill

Security audit

Agent Email Patterns

Security checks for vulnerabilities and agentic risk

Overview

This skill provides design guidance for safer agent email workflows and does not include executable code or hidden high-impact behavior.

This appears safe to install as guidance material. When applying its patterns in a real email integration, verify any external example code separately and keep mailbox permissions scoped, approvals explicit, and incoming message content treated as untrusted.

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.