ClawHub
Back to skill

Security audit

Chinese Restaurants

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed restaurant-finding guide that uses location only for its stated purpose.

Before installing, users should be comfortable sharing location for restaurant search and should expect any implementation to request location permission, avoid retaining precise coordinates, and use only short-term caching as described.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The skill content is primarily written in Chinese but embeds English phrases like "Chinese Restaurants" and "Chinese food near me" as fixed terminology and trigger examples. This imposes a mixed language presentation without stating that users may interact in their preferred language or that the locale is intentionally constrained.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.