ClawHub
Back to skill

Security audit

早餐推荐助手

Security checks across malware telemetry and agentic risk

Overview

This breakfast helper stores local fridge, preference, and recommendation-history files for its stated purpose, with no executable code or network behavior found.

Install if you are comfortable with the skill keeping local records of fridge contents, breakfast history, and any dietary preferences or allergies you tell it. Review or delete files under ~/.openclaw/workspace/breakfast-recommender/ if they become outdated, and only enable scheduled recommendations if you want recurring agent messages.

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
92% confidence
Finding
The dynamic-update triggers are broad natural-language phrases like '买了', '吃完了', and '还剩xxx', which can overlap with ordinary discussion rather than an explicit instruction to modify stored data. Because the skill performs write operations to persistent files based on these phrases, a casual statement or ambiguous context could cause unintended inventory changes and corrupt future recommendations.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill documents automatic creation of persistent files and full overwrite behavior for `fridge.md` without clearly warning the user that their statements may be stored and replace prior data. In this context, silent persistence increases the risk of unintended data loss, privacy surprises, and accidental modification of long-lived personal preference or food-inventory records.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.