ClawHub
Back to skill

Security audit

Consumer Rights

Security checks for vulnerabilities and agentic risk

Overview

This is a China consumer-complaint drafting skill with no executable code, persistence, or hidden behavior, though users should avoid sharing unnecessary personal details.

Install only if you need help drafting China consumer-dispute materials. Provide the minimum facts needed and redact unrelated personal data, addresses, phone numbers, IDs, payment details, and account/order identifiers where possible; verify legal citations and filing routes before submitting anything official.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The workflow explicitly instructs collection of screenshots, receipts, chat logs, tracking numbers, and other evidence that may contain personal, financial, or account data, but it provides no minimization, redaction, retention, or consent guidance. In a legal-dispute context, users are likely to share highly sensitive material, so the absence of privacy safeguards increases the risk of unnecessary exposure or mishandling of personal information.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
75% confidence
Finding

The workflow hard-codes PRC laws, 12315, and China-specific escalation bodies, which imposes a locale-specific framework. Although the description mentions disputes in China, the instructions do not clearly present this as a regional constraint to confirm with the user before proceeding.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.