ClawHub
Back to skill

Security audit

AI视频音频提取 | 提取背景音乐 | 人声提取 | 视频转音频 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill does what it says, but it asks the agent to install and configure an external service with a user API key and to overwrite an existing regional configuration without clear user choice.

Review this before installing if you use qhkit already or care where platform links and API credentials are routed. Only proceed if you are comfortable installing global tools, sending video links to Qinghu/qhkit, and having the agent configure qhkit with a Qinghu API key; avoid sharing long-lived or high-privilege keys directly with the agent when a scoped temporary key is available.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
94% confidence
Finding

The skill declares broad, mandatory activation conditions using common phrases like extracting audio/BGM from videos, which increases the chance of over-triggering in unrelated contexts. In an agentic system, this can cause the skill to intercept user requests too aggressively, leading to unexpected tool use, unnecessary package installation, network access, or handling of untrusted media URLs without clear user intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill instructs the agent to force the domestic Chinese site/configuration and to override existing configuration without user choice, which can redirect users to a specific service environment and influence credential handling. This is risky because it may cause unconsented data routing, incorrect account usage, and social engineering of users into obtaining and providing API keys from a prescribed external site.

Content

No source excerpt is available for this finding.