Back to skill

Security audit

TikTok-商品详情查询 | 青虎AI

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to perform the advertised TikTok product lookup, but it gives the agent broad setup authority to install and run unpinned external tooling for a narrow paid query task.

Review this before installing. It is not showing evidence of deception or data theft, but you should only use it if you are comfortable installing qhkit/Node tooling, storing or providing a Qinghu API token, and incurring Qinghu credit charges after approval. Prefer a pinned qhkit version and avoid persistent PATH/profile changes unless you intentionally want them.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
Findings (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger language is overly broad and mandatory, including phrases like 'or similar requests' and 'must trigger,' which can cause the agent to invoke the skill in contexts where the user did not clearly request this tool. In a paid, externally connected skill that may install software and handle credentials, over-triggering materially raises the risk of unauthorized actions and data exposure.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill goes far beyond product-detail lookup by directing the agent to install Node.js, globally install packages, configure credentials, and troubleshoot the runtime environment. That expands the agent's authority from data retrieval to broad system modification, increasing the attack surface and enabling unnecessary code execution for a relatively narrow task.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The skill instructs use of npx @iqinghu/qhkit without pinning a specific version, which allows whatever package version is current at execution time to be fetched and run. In a skill that can trigger software installation and command execution, this increases supply-chain risk and undermines reproducibility, especially if the package is updated maliciously or incompatibly.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
94% confidence
Finding

This duplicate finding points to the same persistent installation behavior: unpacking Node.js into a user directory and advising PATH changes that can outlive the session. Even though the text notes current-shell scope, it also suggests adding the path to shell startup files, which normalizes durable environment modification for a simple lookup skill.

Content

Scanner excerpt · SKILL.md (reported line 88)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
94% confidence
Finding

This duplicate finding points to the same persistent installation behavior: unpacking Node.js into a user directory and advising PATH changes that can outlive the session. Even though the text notes current-shell scope, it also suggests adding the path to shell startup files, which normalizes durable environment modification for a simple lookup skill.

Content

Scanner excerpt · SKILL.md (reported line 88)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

Static analysis

No suspicious patterns detected.