ClawHub
Back to skill

Security audit

Cart Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only shopping cart discount helper with no code execution, persistence, or credential handling.

Review the final checkout terms yourself before acting on the advice, especially coupon stacking, refundability, shipping, and whether a filler item is actually useful. The skill should not need account credentials or platform session access.

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 (3)

Natural-Language Policy Violations

Medium
Confidence
85% confidence
Finding
The title and full skill description are presented only in Chinese, and the example interactions also assume Chinese-language use. This can indicate a language/locale constraint without explicit user opt-in or justification, which matches the policy concern for forced language behavior.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The usage description says to use the skill when the user asks about broad topics like '优惠券' or 'the cheapest way to reach a promotion tier.' These phrases can overlap with general shopping advice and the file does not provide exclusion conditions or negative examples to clarify when the skill should not activate.

Natural-Language Policy Violations

Low
Confidence
78% confidence
Finding
The skill title, examples, and instructions are partly in Chinese and partly in English, but the document does not state whether the assistant should match the user's preferred language. This can create an implicit language policy constraint without user opt-in.

Static analysis

No suspicious patterns detected.