ClawHub

Shopping List

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward local shopping-list skill that stores list, history, and user-name data locally, with no evidence of hidden network access or behavior outside its own files.

Install only if you are comfortable with a local skill retaining shopping-list state, purchase history, and a saved user name. Review or clear the bundled sample data before use, avoid putting sensitive details in item notes, and use explicit wording for remove or clear actions because removals are not archived.

SkillSpector

By NVIDIA
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 (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill advertises very broad trigger phrases such as generic shopping-list language, which can cause unintended invocation during normal conversation. This creates a safety and privacy risk because the agent may modify persistent household data when the user did not intend to operate the shopping-list skill.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill persistently stores a user identity in config.json and uses it to tag future list entries, but it does not instruct the agent to disclose that this personal data will be retained across sessions. In a shared household context, silent persistence of identity can create privacy surprises, incorrect attribution, and consent issues.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal