Security audit
Security checks for vulnerabilities and agentic risk
The skill is mainly a coherent Shopee shop-data query helper, but it also directs agents to make broad local environment changes and run unpinned external package installs.
Install only if you are comfortable with qhkit, Node/npm, and a Qinghu token being configured on the machine. Prefer installing qhkit through a trusted, pinned setup process first, and do not let the agent modify PATH, shell startup files, or global npm packages without explicit approval.
This markdown/manifest text says the skill '必须触发' not only for a few examples but also for any '同类需求', which leaves the activation boundary unclear. The example phrase '对标店铺列表' is also broad enough that it could overlap with many benchmarking/listing requests beyond this specific Shopee shop-filtering workflow.
The trigger section provides only three example utterances and no negative examples, exclusion conditions, or explicit statement of what related requests should not activate this skill. That ambiguity increases the risk of unintended invocation for adjacent tasks such as broader competitor analysis or general shop research.
The skill goes far beyond querying Shopee shop data by telling the agent to install Node.js, globally install packages, modify PATH, set credentials, and alter local configuration/environment. This expands the attack surface from a narrow data query into arbitrary environment bootstrapping and secret handling, increasing the chance of unsafe system changes, credential exposure, or unintended persistence.
The skill instructs use of npx @iqinghu/qhkit without pinning an exact version, which makes execution dependent on whatever package version is current at runtime. That creates a supply-chain and reproducibility risk: a future compromised or incompatible package release could be fetched and executed automatically in the user's environment.
This duplicate finding points to the same persistence behavior: unpacking Node into the home directory and exporting a new PATH for subsequent command execution. In the context of an agent skill, instructions that reshape the runtime environment create unnecessary persistence and increase the blast radius if the dependency or workflow is later abused.
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:$PATH"
This duplicate finding points to the same persistence behavior: unpacking Node into the home directory and exporting a new PATH for subsequent command execution. In the context of an agent skill, instructions that reshape the runtime environment create unnecessary persistence and increase the blast radius if the dependency or workflow is later abused.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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.