Security audit
Security checks for vulnerabilities and agentic risk
The skill’s Shopee trend-analysis purpose is clear, but it needs review because it tells the agent to install and update runtime tools and configure credentials automatically.
Install only if you are comfortable letting the agent set up qhkit and possibly Node/npm on the machine, store or use a Qinghu API token, and make paid Qinghu data calls after authorization. Prefer a preinstalled, pinned qhkit version and require explicit approval before any package install, upgrade, PATH/profile change, or credential configuration.
The description says the skill must trigger when the user says the listed examples "或提出同类需求时必须触发", which leaves the activation scope undefined beyond two examples. This ambiguity can cause unintended invocation for loosely similar product-analysis requests because there are no explicit exclusions or negative examples.
The trigger example "这款是不是在走下坡路" is broad natural language that could describe many contexts beyond this specific monthly/quarterly/yearly Shopee long-term trend tool. Without qualifiers like platform, product-ID context, or trend-granularity constraints, it risks colliding with everyday analytical requests.
The skill’s stated purpose is querying Shopee product trends, but it also contains extensive environment bootstrapping logic: installing Node, installing npm packages globally, configuring tokens, and modifying runtime setup. That materially expands the agent’s authority from data retrieval into software installation and credential handling, increasing the blast radius if the skill is triggered unexpectedly or manipulated through user input.
The skill instructs the agent to execute an unpinned package via npx @iqinghu/qhkit, which fetches whatever version is current at runtime. This creates a supply-chain risk: a compromised or breaking upstream release could execute unexpected code in the agent environment, especially because the skill also positions this as an automatic fallback when global install fails.
This duplicated finding points to the same persistence behavior: downloading and unpacking a runtime into a user-controlled directory for reuse across commands. In the context of a narrow analytics skill, that is excessive privilege expansion and creates lasting system state changes unrelated to the core business function.
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:$PATH"
This duplicated finding points to the same persistence behavior: downloading and unpacking a runtime into a user-controlled directory for reuse across commands. In the context of a narrow analytics skill, that is excessive privilege expansion and creates lasting system state changes unrelated to the core business function.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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.