ClawHub

Recipe Finder

Security checks across malware telemetry and agentic risk

Overview

This appears to be a recipe-focused skill whose broad triggers and local favorites storage are worth noticing but fit its stated purpose.

Install only if you are comfortable with a recipe skill activating for general food questions and saving favorites or related preferences locally. On a shared device, review the documented storage path and delete saved data if you do not want those preferences retained.

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
91% confidence
Finding
The example trigger phrases are very broad everyday utterances such as asking what to eat or how to cook a common dish. In an agent-routing environment, this can cause accidental invocation from unrelated normal conversation, leading to unintended data exposure to the skill, confusing takeovers of user intent, or inappropriate tool activation.

Missing User Warnings

Medium
Confidence
82% confidence
Finding
The skill declares file read/write access for storing favorites and shows a concrete local storage path, but does not clearly warn users that their recipe preferences and usage metadata may persist on disk. This can create an avoidable privacy risk on shared systems or managed environments where local files may be inspected, backed up, or retained longer than users expect.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal