Back to skill

Security audit

MarketOOH

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only sales workflow skill for China-focused outdoor advertising, with some privacy-related sales language users should handle carefully.

Installers should treat this as a China-focused OOH sales enablement skill. Before using its LBS targeting or measurement claims in real proposals, verify that any location-derived data is authorized, aggregated or consented, and compliant with applicable privacy and advertising rules.

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 (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

This markdown file describes the skill's purpose in broad terms such as 'Complete OOH marketing workflow' but does not specify what user phrases, contexts, or conditions should invoke it. Without explicit trigger boundaries or exclusions, the skill could be matched too broadly in normal marketing-related conversations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file describes behavior that could affect privacy by promising "LBS 数据监测" for measuring effectiveness, but it does not include any warning or disclosure about location-data use, consent, or compliance considerations. Under SQP-2 for markdown files, privacy-impacting behavior should be accompanied by a warning in the skill description.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The text advertises "按小区定向" using precise LBS capabilities, which implicates user/location privacy and potentially sensitive targeting practices. The markdown lacks any caution that such targeting should be lawful, privacy-compliant, and appropriately disclosed to customers.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This section presents location-based monitoring as a selling point but omits any caution about handling location-derived analytics responsibly. For markdown skills, privacy-affecting behaviors should be disclosed so users understand the compliance and data-protection implications.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
71% confidence
Finding

The document centers on Chinese cities, CNY pricing, and China market coverage, which creates a de facto locale constraint. While region-specific skills can be acceptable, this file does not explicitly state that the skill is China-only or offer users a choice of locale/market context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file is entirely Chinese-language content and does not indicate that users can choose another language or that the skill is intentionally limited to a Chinese-speaking or region-specific audience. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.