Security audit

XiaoChi

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Meituan Waimai browsing and summarization guide with no code, persistence, credential handling, ordering, or bulk collection instructions.

Before installing, treat this as a browsing aid for public Meituan Waimai pages only. Do not use it for ordering, logged-in account actions, automated bulk scraping, or attempts to bypass platform controls.

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 (1)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill description uses a broad trigger condition: '当需要访问或自动化美团外卖相关内容时调用' ('invoke when access or automation of Meituan Waimai-related content is needed'). This can match many generic user requests and cause over-selection of the skill, increasing the chance that the agent performs unintended web interaction or data collection in contexts where a narrower tool should be used.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.