ClawHub
Back to skill

Security audit

Nearby Breakfast Spots

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple, disclosed nearby-breakfast search helper that asks for user-authorized location data and does not include executable code or hidden behavior.

Review that the skill will need your location or city to recommend nearby breakfast spots. It appears proportionate, but location-enabled use should stay user-authorized and avoid retaining precise coordinates longer than necessary.

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

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill is primarily documented in Chinese, but it hard-codes English trigger phrases such as "breakfast near me" and a fixed English category value "breakfast-spots". This creates a language policy concern because the skill appears to require or privilege a specific language without explicit user opt-in or a documented locale-specific reason.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.