Security audit
Security checks for vulnerabilities and agentic risk
The skill’s core purpose is coherent, but it needs review because it can persistently install unpinned external tooling and use a paid service with a user-provided token.
Install only if you trust the @iqinghu/qhkit package and are comfortable giving it an API token and paid-credit access. Prefer a sandboxed environment or preinstalled, pinned qhkit version, and require explicit confirmation before any setup that installs software or any call that spends credits.
The metadata says the skill 'must trigger' for broad, natural-language requests such as asking how much a product sold in May or discussing sales trends. Overly broad mandatory activation increases the chance of the skill running in marginal contexts, which can lead to unnecessary external tool use, billing, or environment changes without sufficient user intent validation.
The invocation guidance gives positive examples for when to trigger but lacks clear boundaries for when not to run. In a skill that can invoke paid external tooling and even bootstrap dependencies, poor scoping materially raises the risk of unintended activation and unnecessary privileged actions.
The skill instructs the agent to install Node.js and globally install the qhkit CLI, which modifies the host environment well beyond the narrow purpose of querying product-trend data. This expands the attack surface, introduces persistent software into the host, and could be abused to execute unreviewed code or alter future sessions.
The skill directs the agent to run npx @iqinghu/qhkit without pinning an exact package version. That creates a supply-chain risk because execution may fetch whatever version is current at invocation time, allowing unexpected behavior changes or compromise if the package or dependency chain is tampered with.
This duplicated finding points to the same persistence behavior: unpacking software into a user directory and altering PATH. Such instructions create lasting environmental state and can enable follow-on abuse or unpredictable behavior in future agent operations.
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:$PATH"
This duplicated finding points to the same persistence behavior: unpacking software into a user directory and altering PATH. Such instructions create lasting environmental state and can enable follow-on abuse or unpredictable behavior in future agent operations.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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"
No suspicious patterns detected.