Security audit
Security checks for vulnerabilities and agentic risk
The skill is a legitimate paid live-room lookup integration, but it asks the agent to make broad host-environment changes without clearly requiring user approval first.
Install only if you are comfortable letting the agent install or upgrade Node/qhkit and configure a qhkit token locally. Before use, require explicit approval for any npm, Node, PATH, or shell-profile changes, and confirm the estimated Qinghu credits before allowing paid calls.
The metadata description says requests with broad phrases like checking a live room or live-room data 'must trigger' the skill. Overly broad mandatory activation can cause the agent to invoke this capability in contexts where the user did not clearly request this tool, leading to unnecessary external calls, possible billing, and unintended disclosure of identifiers or account data.
The '何时触发' section provides only short positive examples and no boundary conditions, making it easy for an orchestrator to overmatch ordinary language about livestreams. In a paid external-data skill, ambiguous trigger scope raises the risk of mistaken invocation, unnecessary billing, and data handling outside user intent.
This line requires the tool name and purpose to be told to the user in Chinese ('中文名 + 用途'), which imposes a language choice in the interaction. The file does not offer a language option or state that Chinese is optional, so it can violate language/locale flexibility expectations.
The skill's stated purpose is to query live-room details, but it also instructs the agent to bootstrap the environment, install Node.js, install npm packages globally, configure credentials, and modify execution paths. This expands the skill from a scoped data lookup into host modification and software deployment, increasing attack surface and enabling unnecessary changes to the user's environment.
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
This duplicated finding points to the same persistence behavior: installation into $HOME/.local/lib and PATH manipulation to make that runtime available across commands, potentially even across sessions if added to shell config. In the context of a simple data-query skill, such persistence is disproportionate and materially increases risk by normalizing host reconfiguration for routine use.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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 points to the same persistence behavior: installation into $HOME/.local/lib and PATH manipulation to make that runtime available across commands, potentially even across sessions if added to shell config. In the context of a simple data-query skill, such persistence is disproportionate and materially increases risk by normalizing host reconfiguration for routine use.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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.