ClawHub
Back to skill

Security audit

Dianping-query

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrowly scoped Dianping restaurant lookup guide, with no executable code or persistence, though it may use a logged-in Dianping browser session.

Before installing, be aware that the skill may use an existing Dianping login and could ask you to complete phone/SMS verification. Use it only when you are comfortable with Dianping receiving your searches and account/location context.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description is broadly framed around querying restaurant information and nearby recommendations, but it does not define clear trigger boundaries, exclusions, or guardrails for when the skill should or should not activate. In an agent environment, this can cause overbroad invocation on loosely related requests, leading the agent to navigate external sites and use a logged-in session unnecessarily, which increases the chance of unintended web actions or privacy exposure.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The skill instructions and examples are entirely in Chinese and assume Chinese-language interaction, with no indication that the user can choose another language or locale. This can violate a language-choice policy if the organization requires user opt-in before constraining language or locale.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.