ClawHub
Back to skill

Security audit

TikTok-达人带货选品建联专家 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill is coherent with its stated TikTok influencer research purpose, but users should expect Qinghu API use, token access, charges, and local spreadsheet exports.

Install only if you intend to use Qinghu for TikTok influencer research. Confirm you are comfortable with the agent using a Qinghu API key, sending requests to Qinghu endpoints, spending Qinghu points after your approval, and saving larger retrieved datasets as local files.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly instructs automatic export of datasets to a local file and to continue operating on cached local file paths without first obtaining user consent or warning that data will be written to disk. In this context, the exported data may contain business-sensitive influencer, product, and competitive intelligence, so silent local persistence increases the risk of unintended disclosure, retention, or access by other tools/users on the host.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill tells the agent to obtain API credentials by reading environment variables such as QINGHU_TOKEN or QHKIT_TOKEN, but it does not require an explicit user-facing warning or permission check before accessing them. Environment variables are sensitive secrets, and allowing a skill to silently consume them expands credential exposure and can enable unauthorized third-party API use if the skill is triggered unexpectedly or in a shared environment.

Static analysis

No suspicious patterns detected.