Security audit
Security checks for vulnerabilities and agentic risk
The skill’s ASIN lookup purpose is legitimate, but it tells the agent to install and update local runtimes/packages and configure API credentials on the user’s machine.
Install only if you are comfortable letting this skill provision qhkit/Node tooling and configure a Qinghu API token locally. Prefer a managed or preinstalled qhkit environment, review any npm or Node installation first, and confirm paid calls before allowing the skill to spend Qinghu credits.
The document explicitly says not to configure the host environment, then later provides detailed instructions to install software, alter PATH, and set credentials. This contradiction is dangerous because it can bypass cautious handling and normalize invasive environment changes under the guise of a simple MCP call.
The description says the skill 'must trigger' when the user says phrases like '查一下这个 ASIN' or asks for '同类需求', which is an open-ended condition without clear boundaries or exclusions. This can overlap with general product-information requests and may cause unintended activation beyond narrowly scoped ASIN-detail lookups.
The '何时触发' section lists only a few example phrases but does not define the precise trigger scope or provide negative examples. Without exclusions, requests involving links or vague product questions could be misclassified as requiring this skill.
The skill goes beyond data-query instructions and tells the agent to install Node, install packages globally, set PATH, and configure API credentials in the host environment. This materially increases the attack surface by enabling code execution, environment modification, and secret handling on the user's machine for a task that should be a bounded remote query.
The skill instructs the agent to execute npx @iqinghu/qhkit without pinning an exact version or integrity mechanism. That creates a supply-chain risk because the resolved package version can change over time, and an agent following the instructions could fetch and execute newly published code in the host environment.
This duplicated finding identifies the same persistence behavior: unpacking a runtime into the home directory and altering PATH for subsequent command execution. In the context of an agent skill for ASIN lookup, persistent environment modification is disproportionate and unsafe because it leaves new executable capability on the host system.
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:$PATH"
This duplicated finding identifies the same persistence behavior: unpacking a runtime into the home directory and altering PATH for subsequent command execution. In the context of an agent skill for ASIN lookup, persistent environment modification is disproportionate and unsafe because it leaves new executable capability on the host system.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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.