Security audit
Security checks for vulnerabilities and agentic risk
The skill is a coherent Shopee ranking query integration, but it also tells the agent to auto-install tooling and persist Qinghu credentials/configuration, which merits user review before installation.
Install only if you are comfortable letting the agent install or upgrade qhkit/Node tooling and store Qinghu API credentials for later use. Prefer a pre-provisioned qhkit installation with a pinned version and provide credentials through your platform's secret mechanism rather than ad hoc persistent config when possible.
The trigger language includes a catch-all phrase equivalent to 'must trigger for similar requests,' which is overly broad and can cause the skill to activate outside its intended scope. In context, that is more dangerous because the skill can perform installs, configuration changes, and paid external calls once activated.
The skill's stated purpose is querying Shopee category rankings, but it includes broad environment bootstrapping, package installation, Node installation, and network-retrieval instructions. This materially expands the agent's authority from data access into software provisioning, increasing attack surface and enabling unintended code execution or system modification unrelated to the user task.
The skill instructs use of npx @iqinghu/qhkit without pinning a specific version, which allows execution of whatever package version is current at runtime. In an agent context, this creates supply-chain risk and undermines reproducibility, especially because the skill also frames this as an automatic fallback path during environment setup.
This duplicate finding points to the same persistence behavior: unpacking Node into a user directory and modifying PATH for later command resolution. The security concern is real because the skill is for querying rankings, yet it authorizes durable runtime alteration unrelated to that 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:$PATH"
This duplicate finding points to the same persistence behavior: unpacking Node into a user directory and modifying PATH for later command resolution. The security concern is real because the skill is for querying rankings, yet it authorizes durable runtime alteration unrelated to that business function.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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"
The skill directs the agent to set persistent credentials and alter account configuration using qhkit config set --token <密钥> --env prod and environment variables. Persisting tokens and changing configuration exceed the narrow purpose of querying rankings and can create credential-handling, cross-session leakage, and account-misconfiguration risks.
The phrase '类目周榜' is terse and lacks platform or task context, so it may collide with generic discussion of weekly category rankings rather than a specific request to use this skill. The surrounding section provides examples, but no negative examples or narrowing conditions for this minimal phrase.
No suspicious patterns detected.