Security audit
Security checks for vulnerabilities and agentic risk
The skill’s Amazon price analysis purpose is clear, but it tells the agent to install and upgrade local tooling and persist API credentials with limited user-control safeguards.
Review before installing. Use this skill only if you are comfortable letting an agent install or upgrade qhkit/Node tooling and handle a Qinghu API token. Prefer preinstalling qhkit yourself from a vetted version and providing credentials through a controlled, revocable method rather than letting the skill bootstrap the environment automatically.
The skill instructs the agent to set persistent credentials in the host environment via qhkit config set --token <密钥> or environment variables. This exceeds the minimum required scope and can lead to secrets being stored on disk or in shell environments where other processes, users, or future sessions may access them.
The instructions require that user-provided category keywords be translated into the target site's language before querying, and repeat this as a mandatory step. This imposes a language/locale behavior on user input without offering a choice or opt-in, which matches the policy category for forced language or locale handling.
The skill goes well beyond price-band analysis and instructs the agent to install Node.js, install npm packages, download binaries, modify PATH, and perform environment setup. Expanding a data-query skill into software installation materially increases attack surface and enables code execution and persistent host changes unrelated to the user’s business request.
The skill instructs use of npx @iqinghu/qhkit without pinning an exact version, which allows execution of whatever version is currently resolved from the registry at runtime. In a privileged agent or host environment, that creates a supply-chain risk and makes behavior non-reproducible, especially since the skill also encourages bootstrapping tooling on demand.
This is a duplicate instance of the same persistent-install behavior: downloading and extracting runtime components into the user home directory and changing execution paths. In skill context, that persistence is disproportionate to the stated purpose and increases the chance of unauthorized long-term host modification.
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:$PATH"
This is a duplicate instance of the same persistent-install behavior: downloading and extracting runtime components into the user home directory and changing execution paths. In skill context, that persistence is disproportionate to the stated purpose and increases the chance of unauthorized long-term host modification.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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.