Back to skill

Security audit

OpenClaw大众点评

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed Dianping restaurant lookup workflow and does not contain code, persistence, or hidden high-impact behavior.

Install only if you want the agent to use Dianping in a browser for restaurant searches. Be aware that if you are logged in, searches and page views may use your Dianping session, and any phone or SMS verification should be entered only by you.

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
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
85% confidence
Finding

The description lists generic use cases like users wanting restaurant ratings, recommendations, or nearby food suggestions, but it does not define specific trigger phrases, boundaries, or negative examples. In a manifest/markdown context, this broad wording could overlap with common conversational requests and cause unintended invocation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
72% confidence
Finding

The entire skill description and operating instructions are written only in Chinese and assume Chinese-language queries and workflow, with no indication that users may choose another language or that the restriction is an intentional, documented locale limitation. This can constitute a language/locale policy issue under the rule when no opt-in or justification is provided.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.