ClawHub
Back to skill

Security audit

Review Buying Advisor

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only skill gives product-review shopping advice from public reviews and does not request credentials, persistence, code execution, or hidden local authority.

Installers should understand that this skill may browse or read public product reviews to advise on purchases. For best results, provide a specific product and platform, and treat its recommendation as evidence-based consumer guidance rather than a guarantee.

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
93% confidence
Finding
The example interaction content and expected assistant outputs are presented only in Chinese, which can amount to forcing a specific language/locale on users. The file does not state that the skill is intended only for Chinese-speaking users or provide an opt-in or alternative language option.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill’s trigger language is broad enough to overlap with generic shopping and product-advice requests, which can cause unintended auto-invocation outside narrowly scoped review-analysis tasks. That increases the chance the agent routes unrelated consumer, recommendation, or comparison queries into this skill, producing overconfident advice from incomplete review evidence or displacing more appropriate skills.

Natural-Language Policy Violations

Medium
Confidence
75% confidence
Finding
The skill heavily centers Chinese trigger phrases and Chinese-language example interactions, and one expected output is written entirely in Chinese, but the file does not state that language should follow user preference or provide opt-in for locale. This can violate language/locale policy if the skill defaults to a specific language without user choice.

Static analysis

No suspicious patterns detected.