ClawHub
Back to skill

Security audit

Childcare

Security checks for vulnerabilities and agentic risk

Overview

This skill is not malicious code, but its childcare listing does not match its course-shopping and exam-prep instructions, so users should review it before installing.

Install only if you intended to add a Chinese education/course-selection helper, not a childcare helper. The artifact does not show malicious execution behavior, but its label and description should be corrected before users rely on it for childcare tasks.

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)

Description-Behavior Mismatch

High
Confidence
98% confidence
Finding
The manifest advertises a childcare skill, but the body describes exam preparation and course-shopping functionality. This mismatch can cause the agent to invoke the skill in the wrong context, exposing users to irrelevant or misleading workflows and potentially routing sensitive childcare-related queries into an unrelated service domain. The deceptive scope mismatch is especially risky because users may rely on the declared metadata to judge appropriateness and trust.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The example trigger phrases are generic templates such as asking how to use the skill for a 'specific scenario task' or about 'core functions,' which can match many ordinary requests unrelated to childcare. Overbroad activation language increases the chance of accidental invocation, causing unintended tool use, confusion, or redirection of users into a mislabeled domain. Because this skill is already scope-mismatched, broad triggers make the misrouting problem more dangerous.

Natural-Language Policy Violations

Low
Confidence
81% confidence
Finding
All user-facing description and examples are written only in Chinese, with no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the stated policy, a fixed language without opt-in or documented justification can be a locale-policy issue.

Static analysis

No suspicious patterns detected.