Security audit
Security checks for vulnerabilities and agentic risk
This is a disclosed TikTok Shop product-rank skill that uses qhkit and paid API calls with consent, but users should approve its software installation and qhkit configuration changes.
Install this only if you intend to use Qinghu/qhkit for TikTok Shop product-rank data. Before running it, confirm any npm or Node installation, confirm any qhkit token or site-configuration change, and approve paid qhkit calls only after checking the estimated Qinghu credits.
The trigger text mandates activation for broad, loosely bounded requests and similar phrasing, which increases the chance the skill runs in contexts the user did not clearly intend. Because this skill can install software, alter configuration, and invoke paid external tools, overbroad triggering can lead to unnecessary execution, unexpected charges, or environment changes.
The invocation examples are open-ended and do not constrain when to query, how much data to retrieve, or when to stop for confirmation. In this skill's context, ambiguous examples can push the agent into making paid calls or chaining upstream tools based on incomplete user intent.
The skill instructs use of npx @iqinghu/qhkit without pinning a specific version, which can fetch whatever package version is current at execution time. That creates supply-chain and reproducibility risk: a compromised or breaking upstream release could execute unexpected code in the host environment.
This duplicate finding points to the same persistence behavior: unpacking a runtime into a user-controlled directory and exporting a new PATH. In an agent skill, that is especially risky because it normalizes self-bootstrap behavior that persists beyond the current action and may be triggered automatically.
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:$PATH"
This duplicate finding points to the same persistence behavior: unpacking a runtime into a user-controlled directory and exporting a new PATH. In an agent skill, that is especially risky because it normalizes self-bootstrap behavior that persists beyond the current action and may be triggered automatically.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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 forces a specific site/locale configuration (cn unless the user explicitly says otherwise) and instructs overwriting existing settings. This can cause cross-tenant or account misconfiguration, break other workflows, and direct users to use different credentials than their current environment expects.
No suspicious patterns detected.