ClawHub
Back to skill

Security audit

Home Cook

Security checks across malware telemetry and agentic risk

Overview

This is a simple home-cooking guidance skill with no executable code, hidden behavior, credential use, persistence, or broad system access.

This appears safe to install as a general cooking helper. Users should treat its cooking temperatures and substitution advice as general guidance, and use specialized medical, allergy, or food-safety advice when health risk is involved.

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
95% confidence
Finding
The skill's activation description is very broad and maps to a large set of ordinary cooking-related requests without defining boundaries or exclusions. In an agent routing system, this can cause over-triggering, unnecessary takeover of general conversations, and increased exposure of users' prompts to this skill even when a more specific or safer handler would be preferable.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The 'When to Use' section uses generic triggers like 'someone asks for a recipe' or 'equipment advice' without disambiguation rules, which makes invocation criteria ambiguous. This increases the chance of the skill being selected for loosely related prompts and can degrade routing correctness or bypass more specialized skills or policy checks.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.