Security audit
Security checks for vulnerabilities and agentic risk
The skill’s Shopee keyword-ranking purpose is coherent, but it tells agents to automatically install software and configure credentials in ways users should review first.
Install only if you are comfortable with this skill using qhkit for paid Qinghu/Shopee data calls and with any dependency or token setup being done explicitly under your control. Prefer preinstalling qhkit yourself, pinning package versions, and providing credentials through a managed secret mechanism rather than letting the skill bootstrap the environment automatically.
The description says the skill 'must trigger' for broad, common phrases like weekly hot search rankings or fastest-growing keywords. Over-broad mandatory triggering can cause the wrong skill to activate in unrelated contexts, increasing the chance of unnecessary tool use, paid calls, or execution of the setup/credential instructions embedded later in the file.
The skill goes far beyond querying Shopee keyword rankings by instructing environment bootstrapping, package installation, Node installation, PATH modification, and credential setup. Expanding a data-query skill into system provisioning increases attack surface and encourages execution of privileged or persistent changes unrelated to the user-facing task.
The skill includes system-level software installation instructions, including global npm installs and manual Node binary download/extraction. For a ranking-query skill, this is excessive capability expansion that can lead an agent to alter the host system, create persistence, or execute unreviewed software as part of normal task fulfillment.
The skill recommends fallback execution via npx @iqinghu/qhkit <命令> ... without pinning an exact package version. That creates supply-chain and reproducibility risk because a future or compromised package release could be fetched and executed at runtime, especially in a tool that also handles credentials and paid API access.
This duplicate finding points to the same persistence behavior: installing binaries under the user's home directory and modifying PATH for subsequent command execution. Even with checksum guidance, embedding persistence instructions inside a business-data skill unnecessarily expands privileges and makes accidental host modification more likely.
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:$PATH"
This duplicate finding points to the same persistence behavior: installing binaries under the user's home directory and modifying PATH for subsequent command execution. Even with checksum guidance, embedding persistence instructions inside a business-data skill unnecessarily expands privileges and makes accidental host modification more likely.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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 configure API tokens and inspect environment configuration, including asking users to obtain credentials and set QHKIT_TOKEN or run qhkit config set. That is outside the narrow ranking-query scope and risks credential handling, leakage, and unsafe secret manipulation by an automated agent.
The invocation guidance provides only positive examples and lacks clear exclusions or disambiguation logic. In isolation this is a quality issue, but in this skill it becomes more security-relevant because accidental activation could cascade into paid external calls or system/bootstrap actions.
No suspicious patterns detected.