ClawHub
Back to skill

Security audit

sichuan-cuisine

Security checks across malware telemetry and agentic risk

Overview

This skill is a Sichuan food product development reference skill with no executable behavior or data-access instructions found.

Use this as planning guidance for Sichuan cuisine R&D and food-safety review, but verify regulations for the relevant jurisdiction and do not install the included requirements.txt unless you have a separate, clear need for those packages.

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 trigger condition includes broad catch-all phrasing such as '或类似表述', which can cause the skill to activate for loosely related requests. In an agent environment, over-broad invocation can route users into a specialized workflow unexpectedly, increasing the chance of irrelevant advice, policy bypass through misrouting, or unsafe reliance on domain-specific guidance outside intended scope.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The trigger condition includes “或类似表述” without defining scope or exclusion rules, which can cause the skill to activate on loosely related food, cooking, compliance, or process questions. In an agent setting, ambiguous activation increases the chance of inappropriate routing, overbroad advice, or the model providing specialized food-safety/process guidance when the user did not explicitly request it.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal