ClawHub
Back to skill

Security audit

邮件草稿生成器

Security checks for vulnerabilities and agentic risk

Overview

This is a simple email drafting and template skill with disclosed local draft/template storage and no executable code or hidden behavior found.

Before installing, consider that email drafts and templates may be saved locally in drafts.json and templates.json. Avoid saving sensitive email content unless you are comfortable with that local persistence.

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
Confidence
94% confidence
Finding
The trigger phrases are very generic everyday language such as '写邮件' and '生成邮件', which can cause the skill to activate in situations broader than intended. Overly broad activation increases the chance that unrelated user requests are routed into this skill, leading to unintended handling of user content, incorrect tool behavior, or misuse of stored draft/template functionality.

Static analysis

No suspicious patterns detected.