ClawHub
Back to skill

Security audit

Dianping Query Moss

Security checks for vulnerabilities and agentic risk

Overview

The skill mainly searches restaurant information, but it also normalizes using a named logged-in Dianping account and possible phone/SMS login without clear ownership or consent boundaries.

Review carefully before installing. Use it only with an account you own or are explicitly allowed to use, avoid sharing SMS verification codes through the agent unless the platform provides a secure flow, and prefer anonymous/public Dianping browsing when possible.

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
94% confidence
Finding

The skill instructs use of a pre-authenticated third-party Dianping account and notes that, if not logged in, the user may need to provide a phone number and SMS verification code. Without an explicit user-facing warning and consent flow, this can lead to unintended account sharing, exposure of personal phone credentials, and actions performed under someone else's account. The skill context increases risk because it normalizes bypassing location/account constraints and relies on persistent authenticated state.

Content

No source excerpt is available for this finding.