ClawHub
Back to skill

Security audit

TikTok-视频复刻专家 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed TikTok video-analysis workflow that uses a user-provided Qinghu API token and asks for confirmation before paid data calls.

Install this if you intend to use Qinghu's TikTok data APIs for video/script analysis. Before running it, be comfortable providing or exposing a Qinghu API token, approving possible credit-consuming calls, and having larger result sets exported to local files. For generic marketing copy or non-TikTok scriptwriting, avoid invoking this skill unless you specifically want TikTok clone analysis.

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)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill metadata description says the skill 'must trigger' for a wide set of content-analysis and script-generation requests, using broad keyword-style matching. That can cause unintended invocation on loosely related user queries, increasing the chance the agent fetches external data, requests credentials, or enters a paid workflow when the user did not explicitly ask for this skill.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The example trigger phrases are generic enough to match common marketing or content-planning requests such as 'give me a script template' or 'how should I shoot this product.' In this skill, unintended activation is more dangerous because the workflow instructs the agent to use external HTTP APIs, handle API tokens, and potentially incur paid tool usage after only broad topical matching.

Static analysis

No suspicious patterns detected.