Security audit
Security checks for vulnerabilities and agentic risk
The skill appears to perform the advertised 1688 product search, but it also tells agents to install or update local tooling and persist API credentials, so it needs user review before installation.
Install only if you are comfortable with qhkit being installed or updated locally and with a Qinghu API token being configured for this environment. Prefer a managed or sandboxed install, avoid shell-profile PATH changes unless you intend them, and approve paid calls only after checking the estimated Qinghu credit cost.
The trigger language includes a broad catch-all requiring activation for 'similar requests,' which can cause the skill to run in situations the user did not clearly intend. Because this skill can lead to installation, configuration, and paid external calls, over-broad invocation increases the chance of unsafe or unauthorized actions.
The skill goes beyond product search and directs the agent to install Node.js and npm packages, download binaries, modify PATH, and bootstrap tooling in the local environment. That materially expands the blast radius from a simple data-query skill into arbitrary environment modification and code execution, which is especially dangerous for autonomous agents.
The skill instructs use of npx @iqinghu/qhkit without pinning a specific version, which allows execution of whatever package version is current at invocation time. In an agent context, this creates supply-chain and reproducibility risk because behavior can change unexpectedly or a compromised upstream release could be executed automatically.
This duplicate finding reflects the same persistence issue: the skill adds software under the user's home directory and changes command resolution through PATH updates. Even with checksum verification, the behavior still expands persistence and trust in ways that are inappropriate for a search skill.
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:$PATH"
This duplicate finding reflects the same persistence issue: the skill adds software under the user's home directory and changes command resolution through PATH updates. Even with checksum verification, the behavior still expands persistence and trust in ways that are inappropriate for a search skill.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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 instructs the agent to set persistent credentials via qhkit config set --token and environment variables, causing secrets to be written into local configuration or process environment. This creates credential-handling risk, persistence beyond the current task, and possible leakage to logs, subprocesses, or unrelated future sessions.
The file hard-codes Chinese-language registration, credential-retrieval, and user-facing guidance tied to Chinese sites and terminology, with no indication that users may choose another language or locale. This can violate language/locale policy when used in environments where the user's preferred language is different.
No suspicious patterns detected.