Security audit
Security checks for vulnerabilities and agentic risk
This skill is a focused TikTok Shop data lookup helper that discloses its paid API use, required token, and local tool installation steps.
Before installing, confirm you trust the qhkit npm package and Qinghu account workflow, because the skill may install command-line tooling, store or use a QHKIT token, send product IDs to Qinghu's service, and consume paid Qinghu credits after consent.
The trigger description includes vague language like 同类需求, which broadens activation beyond clearly defined user intents. In an agent setting, overly broad routing can cause unintended invocation of this skill, leading to unnecessary paid API calls, disclosure of user-provided product identifiers to third parties, or incorrect task handling.
The skill instructs use of npx @iqinghu/qhkit without pinning a specific version, which can fetch and execute the latest package at runtime. That creates a supply-chain risk: a compromised upstream package, typo-squat, or breaking release could lead to arbitrary code execution in the agent environment.
The duplicated finding reflects the same persistent-install behavior: unpacking binaries into a user-owned directory and exporting a modified PATH. In an agent context, such self-bootstrap behavior is risky because it normalizes installing and persisting executable tooling during task execution, increasing exposure to supply-chain compromise and cross-session effects.
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:$PATH"
The duplicated finding reflects the same persistent-install behavior: unpacking binaries into a user-owned directory and exporting a modified PATH. In an agent context, such self-bootstrap behavior is risky because it normalizes installing and persisting executable tooling during task execution, increasing exposure to supply-chain compromise and cross-session effects.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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 '何时触发' section provides only three example utterances, but does not state whether activation is limited to those phrases or broader intent-matching conditions. Without scope boundaries or exclusion examples, neighboring intents may be matched too broadly.
No suspicious patterns detected.