Security audit
Security checks for vulnerabilities and agentic risk
The skill’s video-data lookup is coherent, but it also tells an agent to install/update tooling and store API credentials persistently, so it should be reviewed before use.
Install only if you are comfortable letting this skill use the qhkit service for paid video-detail lookups and potentially modify your local Node/qhkit setup. Prefer a sandbox or preinstalled qhkit, use an environment variable or platform secret for the token instead of persistent config, and review any install or upgrade command before it runs.
The manifest says the skill 'must trigger' when the user says two example phrases 'or raises similar needs' (或提出同类需求时必须触发). That leaves the activation scope ambiguous because it does not define what counts as similar, increasing the chance of unintended invocation for loosely related requests about video data or link parsing.
The skill’s stated purpose is querying video details, but it instructs the agent to bootstrap Node.js, install packages globally, and perform environment setup. Expanding from data lookup to software installation materially increases attack surface and gives the skill a path to alter the host environment beyond what is necessary for the user task.
The skill instructs use of npx @iqinghu/qhkit without pinning an exact version, which allows execution of whatever package version is current at runtime. That creates a supply-chain risk: behavior can change unexpectedly or a compromised upstream release could execute arbitrary code in the agent environment.
This duplicate finding points to the same persistence behavior: unpacking software into a user directory and exporting a modified PATH. Even with checksum guidance, the skill is still directing durable host changes unrelated to the minimal act of looking up a video record, which broadens risk unnecessarily.
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:$PATH"
This duplicate finding points to the same persistence behavior: unpacking software into a user directory and exporting a modified PATH. Even with checksum guidance, the skill is still directing durable host changes unrelated to the minimal act of looking up a video record, which broadens risk unnecessarily.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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 tells the agent to persistently configure credentials using qhkit config set --token or environment variables. This exceeds the scope of a simple lookup skill and can lead to sensitive token storage, credential reuse across sessions, and accidental exposure if the environment is shared or later compromised.
No suspicious patterns detected.