ClawHub
Back to skill

Security audit

Claude Email Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a non-executable email workflow guide that emphasizes bounded source material and human approval before live email-system changes.

Before installing, understand that this skill may activate for many email-related planning or improvement tasks. It is appropriate for drafting and review support, but users should still manually approve any live sends, contact imports, DNS/authentication changes, suppression edits, or production automation changes.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description says to use the skill when an AI agent needs to "plan, review, implement, audit, or improve email work," which is a very wide trigger scope. Although examples are given, there are no exclusion conditions or negative examples to clarify when ordinary email tasks should not invoke this skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The default prompt says 'Use $claudeemailskill to help me plan, audit, or improve an email workflow,' which covers very broad intents like 'help me plan' or 'improve' without clear scope boundaries or exclusion conditions. In a manifest file, this can create ambiguous activation behavior because the skill appears applicable to many ordinary email-related requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.