Security audit
Security checks for vulnerabilities and agentic risk
The skill performs the stated TikTok video-detail lookup, but it also directs agents to auto-install and upgrade unpinned tooling, configure tokens, and create persistent local environment changes.
Install only if you intend to use Qinghu qhkit for paid TikTok data lookups and are comfortable with local Node/npm tooling, a Qinghu API token, and credit charges. Prefer a preinstalled, pinned qhkit version, and require explicit approval before any package installation, upgrade, PATH change, or token storage.
The manifest description uses broad trigger language like '查一下这条 TikTok 视频的数据' and related keywords that can match common user requests. This can cause over-triggering of the skill, increasing the chance that the agent invokes a paid external tool or follows risky setup steps when the user did not explicitly request this specific integration.
The trigger section provides only ambiguous example phrases without clear boundaries for when the skill should or should not activate. In context, this is more dangerous because activation can lead to external CLI calls, package installation, token handling, and paid API usage rather than a simple local response.
The skill goes far beyond querying TikTok video details by instructing the agent to install Node.js, install npm packages globally, configure tokens, and upgrade tooling. This expands the trust boundary from a narrow data lookup into environment modification and remote code installation, which materially increases the chance of supply-chain compromise or unintended system changes.
The skill instructs the agent to run npx @iqinghu/qhkit without pinning an exact version or integrity hash. That allows execution of whatever package version is current at invocation time, creating a supply-chain risk if the package is updated maliciously or compromised upstream.
This duplicate finding points to the same persistence behavior: installing binaries under the home directory and changing PATH as part of skill execution guidance. In a skill whose stated purpose is only TikTok video-detail lookup, these instructions are unnecessarily invasive and create long-lived environment state that could be abused by later processes.
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:$PATH"
This duplicate finding points to the same persistence behavior: installing binaries under the home directory and changing PATH as part of skill execution guidance. In a skill whose stated purpose is only TikTok video-detail lookup, these instructions are unnecessarily invasive and create long-lived environment state that could be abused by later processes.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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.