ClawHub
Back to skill

Security audit

Temu

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only shopping advice skill for evaluating Temu listings, with one minor sizing-generalization caveat but no unsafe agent behavior.

Before installing, understand that this skill provides conservative shopping heuristics rather than verified facts. Use it as a checklist, and verify sizing, customs, shipping, safety certifications, and return terms for your own region and seller.

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

Low
Confidence
93% confidence
Finding
This natural-language instruction hard-codes a locale/comparison framework centered on US/EU sizing and a generalized 'Chinese sizing' assumption. The file does not present this as optional, contextual, or region-specific guidance, which can violate language/locale policy expectations requiring opt-in or justified constraints.

Static analysis

No suspicious patterns detected.