ClawHub
Back to skill

Security audit

AgentMailer Security

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only security guidance skill for AgentMailer, with no executable behavior or hidden data access found.

Before installing, be aware that the skill may be invoked automatically for AgentMailer-related security topics. Its content is advisory and should not be treated as permission to send messages, change credentials, or modify configuration without explicit user authorization.

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 narrowing conditions or safeguards, which can cause the agent to auto-apply this security-focused skill in broader contexts than intended. Over-broad activation increases the attack surface for prompt-routing manipulation, accidental disclosure of sensitive workflow details, and unexpected influence over agent behavior when untrusted inputs mention related terms.

Content

No source excerpt is available for this finding.