ClawHub
Back to skill

Security audit

saizeriya

Security checks across malware telemetry and agentic risk

Overview

This is a clearly scoped helper for operating a Saizeriya ordering CLI, with real-world order actions called out for user confirmation.

Install only if you want an agent to operate a Saizeriya ordering session. Review confirmations before submitting orders or calling staff, share only QR/session data for the table you intend to use, and consider a dedicated SAIZERIYA_CLI_HOME or reviewed package versions if local session storage matters to you.

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 (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The default prompt is a generic invocation phrase that automatically routes the model into a high-capability CLI skill without stating user-consent, scope, or safety boundaries. In a skill that can start or resume sessions, inspect account/session state, and manage carts, broad activation increases the chance of unintended execution on ambiguous user requests or prompt-injected contexts.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal