ClawHub
Back to skill

Security audit

What To Eat

Security checks for vulnerabilities and agentic risk

Overview

This is a low-risk meal-picking skill that only uses built-in restaurant and cafeteria lists to suggest what to eat.

This appears safe to install as a convenience meal-decision helper. Be aware it may trigger on broader food-related questions, and its restaurant ratings and options are static unless the publisher updates them.

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
88% confidence
Finding
The trigger scope is overly broad because the manifest says it activates on "any food-related questions," while the body also lists very generic phrases like "吃啥". This can cause unintended invocation on unrelated or sensitive food-domain queries, leading to incorrect routing, suppression of better-suited skills, or confusing responses when the user did not actually ask for a random restaurant recommendation.

Static analysis

No suspicious patterns detected.