Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed video upscaling workflow that uses the qhkit cloud CLI, with expected but important install, upload, API-token, and paid-credit considerations.
Install only if you are comfortable installing/running the qhkit npm CLI, providing a qhkit token, uploading the selected video to the Qinghu service, and spending Qinghu credits after reviewing the estimate. Prefer a pinned qhkit version or an isolated environment if you want tighter supply-chain control.
The description says the skill 'must trigger' whenever users say phrases like '视频糊', '画质差', '要高清化', or '老视频翻新'. These phrases are broad, could arise in ordinary conversation, and the file does not provide exclusion conditions or narrower context limits to prevent unintended invocation.
The '何时触发' section lists short example phrases like '这条视频太糊了' and '老视频翻新' but does not clarify when the skill should not activate. Without explicit boundaries or disambiguation, these examples are too open-ended for reliable invocation control.
The skill expands from video upscaling into system bootstrapping by directing the agent to install Node.js, globally install a CLI, and modify the execution environment. This materially increases the attack surface because a content-processing skill should not need to alter host software state or pull multiple external artifacts before it can run.
The skill instructs use of npx @iqinghu/qhkit without pinning a specific version, which can fetch and execute the latest package at runtime. That creates a supply-chain risk: if the package is compromised or a breaking/malicious release is published, the agent may execute unreviewed code during task fulfillment.
This finding duplicates the same persistence behavior: unpacking Node into a user-controlled directory and prepending it to PATH. In the context of an agent skill, that is risky because it changes future command resolution and can make subsequent tasks rely on software introduced by this skill rather than a trusted system package.
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:$PATH"
This finding duplicates the same persistence behavior: unpacking Node into a user-controlled directory and prepending it to PATH. In the context of an agent skill, that is risky because it changes future command resolution and can make subsequent tasks rely on software introduced by this skill rather than a trusted system package.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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"