ClawHub
Back to skill

Security audit

kuaishou-login

Security checks for vulnerabilities and agentic risk

Overview

This skill is narrowly focused on Kuaishou QR-code login, but it intentionally sends a live login QR code and authenticated page screenshots through the agent.

Review carefully before installing. Use only in a trusted local environment where screenshots and agent logs are not shared, and be aware that anyone who can see the returned QR code during its validity window may be able to initiate the login flow. Prefer completing the QR scan directly in your own browser session and closing or logging out of the session afterward.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs the agent to capture and return a login QR code to the user. A login QR code is a live authentication artifact that can often be reused by anyone who sees it during its validity window, so transmitting it through the agent creates a credential-exposure channel and enables session hijacking or unauthorized account access. In this context, the skill is specifically built around authentication, which makes the screenshot request more dangerous, not less.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.