ClawHub
Back to skill

Security audit

Checkin

Security checks for vulnerabilities and agentic risk

Overview

This skill is text-only and has no executable code, but its advertised check-in purpose does not match its shopping and purchase-guidance instructions.

Review this skill carefully before installing because it is advertised as a check-in and points helper but appears to guide shopping comparisons and purchase-related decisions. It does not show executable or persistent behavior, but the publisher should align the name, description, examples, and scope before users rely on it.

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 skill metadata says it provides daily app check-in reminders and points redemption guidance, but the body defines shopping/product filtering, pricing, logistics, and purchase-decision outputs. This capability mismatch can cause the agent to invoke the skill in unrelated commerce contexts, leading to scope confusion, unsafe routing, and user deception about what the skill actually does.

Natural-Language Policy Violations

Medium
Confidence
89% confidence
Finding
The entire skill description and examples are presented only in Chinese, and there is no indication that the skill supports user language preference or is intentionally limited to a Chinese-speaking or region-specific audience. Under the stated policy, language constraints should be optional or explicitly justified rather than implicitly enforced.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The example prompts are broad and generic, such as asking how to use the skill for a 'specific scenario task' or for 'latest玩法/优惠信息', without clear trigger constraints. Overly open-ended invocation patterns increase the chance the orchestrator will match unrelated user requests and let the skill handle queries outside its intended scope.

Static analysis

No suspicious patterns detected.