Security audit
Security checks for vulnerabilities and agentic risk
This looks like a legitimate Shopee analytics skill, but it gives the agent broad setup authority to install or upgrade tools and store API credentials on the host.
Install only if you are comfortable letting the agent set up or upgrade qhkit/Node and store a Qinghu API token locally. Prefer a preinstalled, pinned qhkit version and a scoped or disposable API key, and confirm charges before any paid Qinghu calls.
The metadata description says requests like product daily sales or price/sales trends 'must trigger', which is overly broad and mandatory. Over-broad auto-invocation can cause unintended activation, unnecessary paid calls, and collection or processing of data when the user's intent is ambiguous.
The invocation examples are short generic phrases and do not define exclusion criteria or disambiguation rules. In context, that makes accidental activation more likely, especially because the skill also contains mandatory trigger language and paid external calls.
For a read-only analytics skill, the environment self-bootstrapping section authorizes installing Node, downloading binaries, modifying PATH, and upgrading packages on the host. This expands the skill's power well beyond querying product trends and creates unnecessary attack surface for host modification and supply-chain abuse.
The skill instructs use of npx @iqinghu/qhkit without pinning an exact version. That allows whatever package version is current at execution time to be fetched and run, increasing supply-chain and reproducibility risk if the package is updated maliciously or incompatibly.
This duplicate finding points to the same persistent install-and-PATH-modification behavior. Persisting runtime components for a simple analytics lookup is unnecessary and increases long-term risk through environment drift and potential reuse of unreviewed binaries.
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:$PATH"
This duplicate finding points to the same persistent install-and-PATH-modification behavior. Persisting runtime components for a simple analytics lookup is unnecessary and increases long-term risk through environment drift and potential reuse of unreviewed binaries.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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 tells the agent to set persistent credentials using qhkit config set --token <密钥> --env prod or environment variables. Persisting secrets in the host environment is broader than the query task and risks credential leakage, reuse across sessions, and unintended exposure to other processes or future skills.
No suspicious patterns detected.