Security audit
Security checks for vulnerabilities and agentic risk
This skill is a coherent TikTok creator-video lookup helper, but users should notice that it installs and runs an external qhkit CLI and may consume paid Qinghu credits.
Install only if you intend to use Qinghu's qhkit CLI for TikTok creator video data. Expect to configure a Qinghu API token, approve paid calls before they run, and possibly install Node/qhkit on the machine. Prefer reviewing or pinning the qhkit package version in controlled environments.
The description says the skill '必须触发' when users say phrases like '这个达人最近发了什么视频', '看他的爆款视频', '达人内容分析' or '提出同类需求'. Several of these are broad natural-language requests, especially '达人内容分析' and '同类需求', and the file does not provide negative examples or clear limits distinguishing when this specific skill should activate versus other analytics skills.
The trigger section provides only three short example phrases, including '看他的爆款视频' and '达人内容分析', but does not specify whether these are exhaustive, what entities must be present, or when the request should not invoke this skill. That ambiguity increases the risk of unintended activation for general content-analysis requests.
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 a security-sensitive agent environment, this creates a supply-chain risk: a compromised upstream release or unexpected breaking change could cause unreviewed code execution during skill use.
This guidance persists a runtime in the user directory and encourages reuse across commands, which can outlive the immediate task and affect future sessions. In agent ecosystems, such persistence is risky because later invocations may trust the modified environment, compounding supply-chain or integrity issues if the installed runtime is replaced or misused.
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:$PATH"
This guidance persists a runtime in the user directory and encourages reuse across commands, which can outlive the immediate task and affect future sessions. In agent ecosystems, such persistence is risky because later invocations may trust the modified environment, compounding supply-chain or integrity issues if the installed runtime is replaced or misused.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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"
These lines instruct the agent to send a specific Chinese domestic-site credential-retrieval message and explicitly avoid international-site guidance unless the user says they use an international account. This imposes a locale/language path by default without offering the user a choice of language or confirming their preferred locale.
No suspicious patterns detected.