ClawHub
Back to skill

Security audit

Mango TV

Security checks for vulnerabilities and agentic risk

Overview

This is a small Mango TV guidance skill with no executable code, install hooks, persistence, credential access, or hidden behavior.

Reasonable to install if you want Chinese-language help with Mango TV content and features. Be mindful that account-related topics such as membership expiry or viewing progress should only be discussed when you intend to share that 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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

文件中的名称、描述和交互示例均仅以中文呈现，未说明是否支持其他语言，也未提供用户语言偏好选择。若该技能面向通用用户，这种默认单一语言约束可能构成语言/locale 策略问题。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The example invocations are extremely broad and generic, such as asking how to use the skill for a 'specific scenario task' or for 'latest玩法/优惠信息', which can overlap with ordinary user phrasing. This raises the chance of accidental skill triggering or over-selection by an agent router, causing irrelevant invocation, user confusion, or unintended exposure of skill behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.