Back to skill

Security audit

TikTok-商品带货直播 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill is for a legitimate paid TikTok product-live lookup, but it also tells the agent to make persistent local toolchain and credential setup changes without a clearly separate user-controlled setup flow.

Review this before installing if you do not want an agent to install Node/qhkit, alter PATH, or configure a qhkit token on your machine. The data lookup and paid-call consent flow are reasonably disclosed, but dependency installation and credential setup should be treated as a separate setup decision.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill goes well beyond querying a data source and instructs the agent to install Node.js, globally install packages, configure credentials, and troubleshoot environment state. This expands the attack surface substantially by encouraging software installation and persistent configuration changes in the host environment for a simple lookup task.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
86% confidence
Finding

The skill instructs use of npx @iqinghu/qhkit without pinning a specific version, which makes execution depend on whatever package version is current at runtime. That creates a supply-chain risk and undermines reproducibility, especially because the package is then used to access tokens and paid remote APIs.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
92% confidence
Finding

This duplicated finding identifies the same persistence behavior: installing software into a user-controlled directory and altering PATH for subsequent use. In context, the persistence is especially risky because the skill also handles token configuration and directs repeated CLI usage, increasing the chance that the installed tooling influences later sessions.

Content

Scanner excerpt · SKILL.md (reported line 93)May include surrounding context.

Linux 二进制安装(装到用户目录,无需 root;先校验官方 SHA256 再解包):

cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | sha256sum -c - mkdir -p "$HOME/.local/lib" && tar -xJf /tmp/node-v22.22.3-linux-x64.tar.xz -C "$HOME/.local/lib" export PATH="$HOME/.local/lib/node-v22.22.3-linux-x64/bin:$PATH"

text

Session Persistence

Medium
Category
Rogue Agent
Confidence
92% confidence
Finding

This duplicated finding identifies the same persistence behavior: installing software into a user-controlled directory and altering PATH for subsequent use. In context, the persistence is especially risky because the skill also handles token configuration and directs repeated CLI usage, increasing the chance that the installed tooling influences later sessions.

Content

Scanner excerpt · SKILL.md (reported line 93)May include surrounding context.

Linux 二进制安装(装到用户目录,无需 root;先校验官方 SHA256 再解包):

cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | sha256sum -c - mkdir -p "$HOME/.local/lib" && tar -xJf /tmp/node-v22.22.3-linux-x64.tar.xz -C "$HOME/.local/lib" export PATH="$HOME/.local/lib/node-v22.22.3-linux-x64/bin:$PATH"

text

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
81% confidence
Finding

The instructions explicitly require sending the domestic-site credential guidance text to the user, and that guidance is written only in Chinese. This imposes a specific language/locale on user-facing communication without offering a language choice or documenting a justified locale restriction for all users.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.