ClawHub

goods-search-v2

Security checks across malware telemetry and agentic risk

Overview

This is a coherent shopping search skill that sends user-provided shopping queries to an external AISearch service, with privacy cautions but no evidence of hidden or destructive behavior.

Install only if you want shopping searches handled through the external AISearch provider. Use a scoped provider API key, avoid sending sensitive images or precise location unless needed, and treat user, nickname, and location fields as optional personal data rather than defaults.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
80% confidence
Finding
The trigger phrases are extremely broad and cover common shopping verbs and nouns, which can cause the skill to activate for many ordinary conversations. Overbroad activation increases the chance of unintended tool invocation, unnecessary data sharing to backend search services, and user confusion when the assistant is forced into this skill instead of handling the request locally or with a more appropriate tool.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The documentation instructs clients to send API-key-authenticated requests that may include user identifiers, nicknames, images, and precise location data, but it provides no privacy notice, consent guidance, minimization advice, or handling restrictions. In a shopping/search skill that is meant to be invoked broadly for user queries, this omission increases the chance that integrators will collect and transmit personal data without adequate user awareness or controls.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal