Security audit
Security checks for vulnerabilities and agentic risk
This appears to be a legitimate paid Qinghu video-comment lookup skill, but it also directs agents to make host setup changes such as global/unpinned package installs and local Node installation, so it needs user review before use.
Install only if you are comfortable letting the agent set up qhkit/Node tooling and configure a Qinghu API token. Confirm any dependency installation or PATH change yourself, prefer a pinned qhkit version, and make sure each paid call and credit spend is explicitly approved.
The trigger phrase 评论区反馈 is broad and could match ordinary conversation about comments or feedback, causing unintended activation of this paid/external-data skill. In context, accidental activation is more concerning because the skill may initiate billable calls and guide the agent into setup or credential workflows unrelated to the user's actual intent.
The skill's stated purpose is querying video comments, but it contains extensive instructions to install Node, install packages globally, set API tokens, and modify environment configuration. This broadens the skill from data retrieval into host bootstrap and persistent system changes, increasing attack surface and enabling unintended code execution or credential handling on the host.
The skill instructs use of npx @iqinghu/qhkit without pinning a specific version, which permits execution of whatever package version is current at runtime. That creates supply-chain and reproducibility risk: a compromised, malicious, or breaking upstream release could be fetched and executed in the user's environment during skill use.
This duplicate finding points to the same session-persistence behavior: unpacking software into a user-controlled directory and adjusting PATH so future commands prefer the newly installed binaries. In a skill context, that exceeds least privilege and creates an unnecessary persistence mechanism that could survive the immediate task and alter subsequent command execution trust boundaries.
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:$PATH"
This duplicate finding points to the same session-persistence behavior: unpacking software into a user-controlled directory and adjusting PATH so future commands prefer the newly installed binaries. In a skill context, that exceeds least privilege and creates an unnecessary persistence mechanism that could survive the immediate task and alter subsequent command execution trust boundaries.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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.