Security audit
Security checks for vulnerabilities and agentic risk
The skill’s TikTok comment lookup purpose is clear, but it directs agents to install or upgrade tools, alter the user environment, and configure API tokens on the host.
Install only if you are comfortable letting the agent install or upgrade Node/npm tooling, use qhkit from npm, and configure a Qinghu API token on your machine. Prefer a preinstalled, pinned qhkit version and platform-managed secrets, and confirm costs before any paid comment retrieval.
The trigger description includes broad, catch-all wording such as 'or similar requests must trigger', which can cause the skill to activate on loosely related user messages. Over-broad invocation is risky here because the skill can lead to package installation, credential setup, and paid external calls rather than a narrow read-only lookup.
The example trigger phrases are common conversational language and may overlap with generic requests about comments or public sentiment. In this skill's context, accidental activation is more dangerous because invocation may initiate external tool use, authorization flow, and potentially paid operations.
The skill's stated purpose is to retrieve TikTok video comments, but it also instructs the agent to bootstrap Node.js, install global packages, upgrade tooling, and modify the execution environment. This expands scope from data retrieval to host modification, increasing the chance of unintended code execution, persistence, and supply-chain compromise.
The skill instructs use of npx @iqinghu/qhkit without pinning a specific version, which allows execution of whatever package version is current at runtime. That creates a supply-chain risk and makes behavior non-deterministic, especially because the same file also encourages installation and execution on the host environment.
This duplicated finding identifies the same persistence behavior: unpacking software into the user's home directory and exporting a modified PATH. Such changes outlive the specific comment-query task and can influence later command resolution, creating a durable foothold for unintended or compromised tooling.
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:$PATH"
This duplicated finding identifies the same persistence behavior: unpacking software into the user's home directory and exporting a modified PATH. Such changes outlive the specific comment-query task and can influence later command resolution, creating a durable foothold for unintended or compromised tooling.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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 credentials in the host environment using qhkit config set or environment variables, including persistent token setup. This crosses a major security boundary by causing the agent to handle and store secrets on the host, potentially exposing credentials to logs, shell history, other processes, or later sessions.
No suspicious patterns detected.