ClawHub
Back to skill

Security audit

meitu

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language guidance skill for elderly/home-service selection, with some scope-quality issues but no hidden code, persistence, credential use, or unsafe execution behavior.

Review whether the Chinese-only wording and generic home-service filters match your intended elderly-care workflow. It should not be treated as medical, legal, or formal care-placement advice, and users should verify providers, qualifications, insurance, and local service availability before acting.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
The skill’s description and all user-facing instructions are written only in Chinese, with no indication that the user can choose another language or that the skill is intentionally limited to Chinese-speaking or region-specific use. This creates a natural-language locale constraint without opt-in, which matches the language/locale policy violation criteria.

Description-Behavior Mismatch

Medium
Confidence
94% confidence
Finding
The skill content does not match the declared elderly-care purpose and instead describes a generic home-service booking workflow. This can cause the agent to trigger in the wrong contexts, route users toward unrelated or unsafe services, and undermine safeguards expected for elderly-care scenarios where accuracy and trust are especially important.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The example trigger phrases are overly broad and resemble ordinary help-seeking language, which increases the chance of unintended activation. In an elderly-care context, accidental routing to this skill could produce irrelevant guidance or missed intent handling when users are seeking time-sensitive care, facility, or safety information.

Static analysis

No suspicious patterns detected.