ClawHub
Back to skill

Security audit

AgentMailer CLI

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent AgentMailer CLI guide, but it allows automatic invocation for broad account-sensitive operations such as sending, domains, webhooks, policy, and billing.

Review this skill before installing if your AgentMailer account has production, billing, domain, webhook, policy, or send privileges. Prefer scoped API keys, require explicit confirmation for mutating commands, use dry-run where available, cap bulk reads, and avoid AGENTMAILER_INSECURE outside local debugging.

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
94% confidence
Finding

The skill enables implicit invocation with no trigger constraints, exclusions, or user-confirmation guardrails. Because this skill exposes shell-based operations over messaging, domains, webhooks, billing, and policy resources, broad automatic invocation can cause unintended execution of sensitive account actions from ambiguous prompts or prompt-injection-influenced workflows.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.