ClawHub
Back to skill

Security audit

Bakery

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language bakery shopping guidance skill with no executable code, persistence, credential handling, or hidden privileged behavior.

Before installing, note that the skill appears intended for Chinese-language bakery shopping assistance and may be less useful outside that context; otherwise it is low risk based on the inspected artifact.

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

文件中的描述、标题、示例请求和注意事项均以中文固定呈现，但未说明该技能仅面向中文用户，亦未提供语言/地区选择。按规则，若技能在自然语言层面默认强制特定语言且无用户选择或合理说明，属于语言/locale 策略问题。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The example trigger phrases are highly generic and overlap with normal help-seeking language, which can cause accidental invocation of the skill in unrelated conversations. In a shopping-oriented skill, this mainly creates routing confusion, unintended activation, and possible disclosure of user shopping intent to the wrong skill rather than direct code execution or privilege escalation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.