Security audit
Security checks for vulnerabilities and agentic risk
The skill’s Shopee brand-analysis purpose is clear, but it tells the agent to install and upgrade unpinned tooling and Node.js during use, which is too much host-environment control for a narrow query skill.
Review before installing. The data-query behavior and paid-call consent rules are reasonable, but do not let the skill automatically install or upgrade qhkit/Node.js unless you trust that npm package and want host-level tooling changes. Prefer preinstalling a pinned, reviewed qhkit version and providing tokens only when needed.
The manifest description is entirely framed in Chinese and says requests using specific Chinese phrases '必须触发', but it does not offer any language choice or state that Chinese is optional. This can violate language/locale policy by implicitly requiring a specific language for activation without user opt-in.
The skill goes far beyond its stated purpose by instructing the agent to install Node.js, download binaries, install npm packages, and configure API tokens. That significantly expands the attack surface from a narrow data-query skill into environment modification and remote code acquisition, creating supply-chain and privilege/persistence risks if the instructions are followed automatically.
The skill instructs use of npx @iqinghu/qhkit without pinning a specific version, which allows whatever package version is current at execution time to run. In a security-sensitive agent context, this creates a supply-chain risk and makes behavior non-reproducible, especially because the package is later used to access credentials and invoke remote services.
This duplicate finding identifies the same persistence behavior: extracting Node into a user directory and exporting a modified PATH. In the context of an agent skill, that is dangerous because it changes the host environment outside the narrow query workflow and can influence subsequent sessions or tasks.
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:$PATH"
This duplicate finding identifies the same persistence behavior: extracting Node into a user directory and exporting a modified PATH. In the context of an agent skill, that is dangerous because it changes the host environment outside the narrow query workflow and can influence subsequent sessions or tasks.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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.