ClawHub
Back to skill

Security audit

Tianmao

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Tmall shopping assistant that can automate browsing and cart preparation but explicitly stops before payment or final order submission.

Install only if you want an assistant to help with Tmall shopping in a logged-in browser. Review its actions before login, cart changes, coupon application, address confirmation, or order preview, and complete payment yourself as the skill requires.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The example trigger phrase is broad enough to overlap with ordinary shopping-assistance requests, which can cause the skill to activate when the user did not specifically ask for Tmall-focused or browser-automation behavior. In this skill’s context, unintended activation is more concerning because the documented workflow includes automated browsing, store verification, coupon checks, cart modification, and order preview generation, all of which can steer or act on a shopping session without sufficiently explicit user intent.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 269)May include surrounding context.

md
- ❌ Recommend non-official stores for branded goods
- ❌ Store user data persistently
- ❌ **Execute payment or final order submission**
- ❌ Guarantee authenticity without verification

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The markdown mixes operational requirements and examples that assume Chinese-language site elements and terms such as 官方旗舰店, 店铺券, 平台券, and 88VIP without stating that the skill is intentionally limited to Chinese/Tmall workflows. Because the file does not offer a language or locale choice or explain a region-specific restriction, this reads as a locale constraint imposed without user opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.