ClawHub
Back to skill

Security audit

cold-email

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese cold-email drafting skill with disclosed research and optional sending steps, and I found no hidden code, persistence, or credential misuse.

Install this only if you want a Chinese-market cold-email drafting workflow. Review generated messages for consent, unsubscribe handling, accuracy of public-source hooks, and compliance with the rules that apply to your recipient list before sending. If you connect an email MCP, ensure the agent only sends after you approve recipients, volume, and cadence.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest description and the instruction body are written as a Chinese-only cold email writing skill, with output requirements and examples exclusively in Chinese and no indication that the user can choose another language. This creates a language/locale policy issue because it implicitly constrains the skill to a specific language without explicit user opt-in or a documented region-specific justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.