ClawHub
Back to skill

Security audit

AgentMailer Toolkit

Security checks for vulnerabilities and agentic risk

Overview

This skill is a guidance package for AgentMailer integrations that discloses its communication purpose and recommends appropriate safeguards for message and event handling.

Before installing, ensure your host runtime requires explicit approval for sending messages, separates read-only and mutating tools, validates recipients, and stores AgentMailer credentials only in the host application.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill enables implicit invocation with no visible trigger constraints, allowing the host agent runtime to invoke the toolkit automatically based on broad matching rather than explicit user intent. Because this toolkit adds communication capabilities, unintended invocation could cause unauthorized message sending, event handling, or interaction with external systems, increasing the risk of prompt-triggered misuse or surprise side effects.

Content

No source excerpt is available for this finding.