Security audit
Security checks for vulnerabilities and agentic risk
The skill’s TikTok ranking lookup purpose is coherent, but it asks the agent to make broad local software and credential changes before running a paid data query.
Install only if you are comfortable letting this skill set up qhkit/Node tooling and handle a Qinghu API token on the local machine. Prefer a preinstalled, pinned qhkit version and provide credentials through a managed secret mechanism rather than shell history or persistent config.
The skill directs package installation, Node setup, PATH changes, and other host-level modifications that are not justified by a video-ranking lookup function. Even if framed as convenience, these instructions can persist changes on the machine and create opportunities for supply-chain compromise or abuse of the host beyond the skill's stated purpose.
The skill tells the operator to set API credentials in the host environment and provides account/login instructions to obtain them. Handling secrets at skill level is risky because it encourages credential exposure, persistence in shell history or environment variables, and use of sensitive tokens for a task that should be abstracted behind platform controls.
The manifest says the skill 'must trigger' when the user provides the listed examples 'or similar needs', which is ambiguous and expands activation beyond clearly bounded phrases. This can overlap with general requests about popular videos or benchmarking without defining exclusions or scope constraints.
The trigger example '找对标爆款视频' is broad and does not clearly state that the request is specifically for TikTok video ranking data. A user could say this in many contexts, causing unintended invocation without additional qualifiers.
The skill claims to only perform a TikTok rank query, but it includes instructions to install software, configure tokens, and modify the host environment. This scope expansion is dangerous because it normalizes privileged host operations unrelated to the narrow user intent, increasing the attack surface and enabling unintended code execution paths.
The skill instructs use of npx @iqinghu/qhkit without pinning an exact version, which allows execution of whatever package version is current at runtime. That creates a supply-chain and reproducibility risk, especially because the skill also encourages installing and running host-side tooling for a simple data-query workflow.
This is the same persistence issue in duplicated analysis output: the skill modifies user-local directories and shell PATH for future command resolution. For a data-query skill, that persistence is unjustified and expands the blast radius if the installed runtime or subsequent commands are compromised.
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:$PATH"
This is the same persistence issue in duplicated analysis output: the skill modifies user-local directories and shell PATH for future command resolution. For a data-query skill, that persistence is unjustified and expands the blast radius if the installed runtime or subsequent commands are compromised.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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"
No suspicious patterns detected.