Security audit
Security checks for vulnerabilities and agentic risk
The skill appears intended for legitimate product-video generation, but it can automatically install and update external tooling on the host and configure a paid API token without a clear user-confirmation boundary.
Install only if you are comfortable letting the agent install or update qhkit/Node tooling, configure an iqinghu API token, upload product media to the service, and spend account credits. Prefer preinstalling and pinning the CLI yourself, then use the skill only after confirming the exact files, duration, model, and estimated cost.
The description says requests for several broad categories of product video 'must trigger' the skill, with little exclusion logic. That can cause unintended invocation in ambiguous contexts, increasing the chance that installation, configuration, or external tool execution occurs when the user did not clearly request it.
The description and operational guidance are written entirely in Chinese and include mandatory behavior phrased for Chinese-language usage, without indicating that other languages are supported for the user-facing interaction. This can violate language/locale policy when a skill forces a specific language without user choice.
The skill's purpose is generating sales videos, but it also instructs the agent to install Node.js, install packages globally, modify PATH, and bootstrap tooling on the local machine. Expanding scope from content generation to system provisioning increases the attack surface and can lead to unintended code execution or persistent environment changes on the host.
The skill includes commands that install software globally, download binaries, and alter environment variables, but these system modifications are not prominently disclosed up front before the operational instructions. Users or agents may therefore make lasting host changes without informed consent, which is risky in a skill ostensibly focused on media generation.
The skill recommends invoking npx @iqinghu/qhkit without pinning a specific version, which makes execution dependent on whatever package version is current at runtime. That creates a supply-chain and reproducibility risk: a newly published or compromised package version could change behavior or execute unexpected code on the host.
The same setup flow explicitly installs binaries under the user's home directory and advises environment changes that can persist beyond the immediate task. Even with checksum verification, this is still a host modification pattern that exceeds the minimum privileges needed for video generation and increases long-term exposure if the toolchain is later abused.
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:$PATH"
The same setup flow explicitly installs binaries under the user's home directory and advises environment changes that can persist beyond the immediate task. Even with checksum verification, this is still a host modification pattern that exceeds the minimum privileges needed for video generation and increases long-term exposure if the toolchain is later abused.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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"