ClawHub
Back to skill

Security audit

1688 Sourcing Agent

Security checks for vulnerabilities and agentic risk

Overview

This is a guidance-only 1688 sourcing skill with no executable code or hidden persistence; the only notable issue is a mildly broad example prompt.

Before installing, treat the skill as procurement guidance rather than a guarantee: verify exchange rates, supplier claims, certifications, payment terms, customs requirements, and regulated-product obligations independently before spending money or placing orders.

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

Low
Confidence
90% confidence
Finding
The example trigger "Help me verify this supplier [link]" begins with a very common conversational phrase and the skill does not provide exclusion conditions or tighter activation constraints nearby. In markdown skill descriptions, broad help-style phrasing can make invocation boundaries less specific and increase the chance of unintended matching.

Static analysis

No suspicious patterns detected.