ClawHub
Back to skill

Security audit

goods_search

Security checks for vulnerabilities and agentic risk

Overview

This shopping search skill is mostly purpose-aligned, but it bundles and automatically uses an undeclared external API key.

Review before installing. The search functionality matches the stated purpose, but the bundled API key should be removed or rotated and replaced with a user-provided, scoped credential. Users should also expect shopping queries, image inputs, optional user fields, and optional location context to be sent to Volcengine AI Search.

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
89% confidence
Finding
The trigger phrases are very broad and cover common shopping language such as 'search', 'recommend', and 'help me find', which can cause the skill to activate in many ordinary conversations. Because the description says it must be used preferentially and discourages direct answering, this overreach can hijack routing, send more user queries than necessary to an external search service, and reduce user control over when data leaves the host system.

Static analysis

No suspicious patterns detected.