Security audit
Security checks for vulnerabilities and agentic risk
The skill’s video-generation purpose is coherent, but it asks the agent to install and upgrade tooling globally and configure persistent credentials without a clear user-consent gate.
Install only if you are comfortable letting the agent install or upgrade qhkit/Node tooling, store or use a qhkit API token, upload the provided media assets to the service, and potentially spend service credits on generated videos. Prefer reviewing any install, upgrade, token configuration, and paid generation step before it runs.
The skill metadata and user-facing description are entirely in Chinese and line L62 explicitly instructs using domestic-site Chinese guidance, with no indication that the user may choose another language. This creates a locale/language constraint without documented opt-in or a clearly justified region-specific limitation in the skill policy text.
The skill expands its behavior far beyond video analysis by directing the agent to install Node.js, globally install and upgrade a CLI, and troubleshoot package management. That grants the skill software-installation and environment-modification capability, increasing the attack surface and enabling execution of remote code from external package registries unrelated to the user's immediate request.
The instructions tell the agent to perform system-changing actions such as global package installation and PATH/profile modification, but do not require an explicit warning and consent flow before making those changes. In an agent setting, this can lead to silent environment drift, unexpected privilege use, and persistence of tooling that the user did not knowingly authorize.
The skill instructs the agent to execute npx @iqinghu/qhkit without pinning an exact version, which allows whatever package version is current at execution time to run with the agent's privileges. Because npx fetches and executes remote code on demand, a compromised publisher account, malicious update, or dependency-chain attack could immediately turn this skill into arbitrary code execution.
This duplicate finding reflects the same persistence issue: the instructions establish software under the user's home directory and alter command lookup behavior via PATH. In the context of an agent skill, persistence is riskier because the user may not realize the environment has been modified for future sessions and tasks.
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:$PATH"
This duplicate finding reflects the same persistence issue: the instructions establish software under the user's home directory and alter command lookup behavior via PATH. In the context of an agent skill, persistence is riskier because the user may not realize the environment has been modified for future sessions and tasks.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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"