ClawHub
Back to skill

Security audit

TikTok-单品分析师 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed TikTok product-analysis helper that uses a Qinghu API token and asks for confirmation before API calls.

Install this only if you intend to use Qinghu's TikTok product-analysis API. Be aware that it can send product queries and your Qinghu bearer token to iqinghu.com, may consume Qinghu credits after you approve tool use, and may create exported data files for larger results.

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
95% confidence
Finding

The manifest states the skill 'must trigger' for a wide range of broad intents, which pressures orchestration to prefer this skill even when the user's request is only loosely related. In context, this increases the chance of unnecessary invocation of a skill that collects credentials, calls external paid APIs, and may export local files, amplifying cost, privacy, and data-handling risks from misrouting.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger section is broad enough to capture generic product-analysis requests such as 'this product sells well' or 'should I stock it', which may cause the agent to invoke this skill in situations better handled by other skills or by a normal conversational response. Because this skill is tool-using and potentially paid, over-triggering can lead to unnecessary external API calls, wasted credits, and unintended disclosure of user-supplied product data to a third-party service.

Content

No source excerpt is available for this finding.