Security audit
Security checks for vulnerabilities and agentic risk
This skill has a clear Douyin video-data purpose, but it also tells the agent to install tooling, configure persistent credentials, and prefer a specific account site with too little user control.
Install only if you are comfortable with qhkit, Qinghu account credentials, paid API usage, and local tooling changes. Prefer using a preinstalled qhkit in a contained environment, approve any credential setup or package installation explicitly, and avoid unpinned npx/latest upgrade paths when possible.
The top-level description uses broad trigger language around Douyin video data that can match common user phrasing without enough narrowing conditions. Over-broad invocation can cause the wrong skill to activate, leading to unexpected external calls, paid actions, or disclosure of user-provided links to third-party tooling.
The invocation section lists ambiguous examples like '看看这个视频的数据' without constraints, which can match many ordinary requests unrelated to this paid external tool. In context, mistaken activation is more dangerous because the skill is designed to drive API calls, pricing flows, and external link processing.
The skill goes far beyond simple video-data lookup and instructs the agent to install Node.js, install global packages, modify PATH, and configure persistent API credentials. That materially expands the trust boundary and gives a content-level skill authority to alter the host environment, increasing the chance of persistence, credential exposure, and unintended system changes.
The skill instructs use of npx @iqinghu/qhkit without pinning a specific version, which can fetch whatever package version is current at execution time. In a skill that also directs installation, credential setup, and paid API usage, this creates a supply-chain and reproducibility risk because behavior may change unexpectedly or a compromised upstream release could be executed.
The skill instructs unpacking software into $HOME/.local/lib and modifying PATH, creating semi-persistent changes to the user environment outside the skill's stated purpose. Even if framed as convenience, this establishes a foothold for future command resolution changes and increases the blast radius if the installed toolchain is later abused or replaced.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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"
The skill instructs unpacking software into $HOME/.local/lib and modifying PATH, creating semi-persistent changes to the user environment outside the skill's stated purpose. Even if framed as convenience, this establishes a foothold for future command resolution changes and increases the blast radius if the installed toolchain is later abused or replaced.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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"
The skill hardcodes a China-domestic account and credential flow unless the user explicitly states otherwise, steering users toward a specific site and token setup. This is risky because it can push users into unnecessary credential provisioning, create account/region confusion, and override user or platform defaults in a way that broadens exposure to external services.
No suspicious patterns detected.