ClawHub
Back to skill

Security audit

TikTok-蓝海爆品采集师 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent TikTok product research helper that uses a disclosed Qinghu API, but users should understand it may use an API token, consume credits, and export result files locally.

Install this if you want Qinghu-powered TikTok product research and 1688 sourcing. Be prepared to provide a Qinghu API token, approve external API calls that may consume Qinghu credits, and manage any exported spreadsheet or cached data files containing your product research.

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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill metadata says it 'must trigger' for a broad set of common TikTok product-research requests, which can cause the agent to invoke this skill too aggressively even when the user did not explicitly want Qinghu/TikTok/1688 data collection. Over-invocation increases the chance of unnecessary external API use, credential prompting, and paid tool calls, creating consent, privacy, and cost risks rather than a direct code-execution issue.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs automatic export of datasets to table files and to reuse local cached file paths without first warning the user that data will be written to local storage. This can create unintended data persistence and disclosure risk, especially if exported files contain commercially sensitive research, account-derived data, or are accessible to other tools, users, or later workflow steps in the environment.

Content

No source excerpt is available for this finding.