Security audit
Security checks for vulnerabilities and agentic risk
The skill is a coherent Shopee keyword-analysis integration, but it asks the agent to modify the local software environment and store credentials without clearly requiring user approval for setup.
Install only if you trust the Qinghu qhkit package and are comfortable letting the agent set up or update local Node/npm tooling and store a Qinghu API token. Prefer a platform-managed or already-installed qhkit, approve any install or credential changes explicitly, and review estimated Qinghu credit costs before allowing paid calls.
The manifest says the skill 'must trigger' when the user says several example phrases 'or raises similar needs' (或提出同类需求时必须触发). That open-ended clause does not define clear limits on what counts as a matching request, increasing the chance of unintended invocation beyond the listed examples.
The skill goes well beyond describing analytics usage and instructs the agent to install Node, install global packages, configure credentials, and modify the local environment. That materially expands the attack surface: a simple data-query skill should not be able to bootstrap software stacks and secrets handling on the host, because this can lead to unauthorized code execution and persistence-enabling changes.
The skill instructs use of npx @iqinghu/qhkit without pinning a specific version, which can fetch and execute whatever package version is current at invocation time. In a skill context, that creates a supply-chain risk and makes behavior non-reproducible, especially because the package is then used to access tokens and make networked MCP calls.
This duplicate finding identifies the same persistence behavior: installing Node under the user's home directory and modifying PATH creates a durable execution foothold for future commands. Even with checksum verification, persisting a new runtime is beyond the scope of a keyword-analysis skill and increases the blast radius of any subsequent compromise or misuse.
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:$PATH"
This duplicate finding identifies the same persistence behavior: installing Node under the user's home directory and modifying PATH creates a durable execution foothold for future commands. Even with checksum verification, persisting a new runtime is beyond the scope of a keyword-analysis skill and increases the blast radius of any subsequent compromise or misuse.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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 short example phrases, without clarifying whether they are exhaustive, what required context must be present, or which related requests should be excluded. For a user-invocable skill, this leaves activation scope ambiguous.
No suspicious patterns detected.