Security audit
Security checks for vulnerabilities and agentic risk
This skill has a legitimate narrow purpose, but it asks the agent to install and update software, alter the local environment, and configure third-party API credentials in ways that deserve review before use.
Install only if you are comfortable letting the skill use the Qinghu qhkit CLI, make paid API calls after consent, and store or use a Qinghu API token. Prefer preinstalling a vetted qhkit version yourself and providing credentials through a controlled secret mechanism instead of allowing automatic global installs, unpinned npx execution, PATH changes, or shell startup modifications.
The keyword list is broad and overlaps with ordinary discussion of WeChat Channels and account topics, increasing the chance of accidental activation. In this skill, accidental activation is more dangerous because the skill also contains instructions for paid calls, software installation, and credential configuration.
The keyword list is broad and overlaps with ordinary discussion of WeChat Channels and account topics, increasing the chance of accidental activation. In this skill, accidental activation is more dangerous because the skill also contains instructions for paid calls, software installation, and credential configuration.
The skill goes far beyond a narrow account-info lookup by directing the agent to bootstrap Node, install packages, modify PATH, and perform environment setup on the host. This materially expands the attack surface from a simple data lookup into host-level software installation and execution, which is dangerous if the skill content is adversarial or triggered unexpectedly.
The skill instructs the agent to run an unpinned package via npx (npx @iqinghu/qhkit), which allows whatever version is current at execution time to be fetched and executed. In an agent context, this creates supply-chain risk and undermines reproducibility, especially because the package is then used to access external services and process user-driven inputs.
This duplicate finding points to the same persistence behavior: installation into a user-controlled directory and PATH modification for future command resolution. Even though the text mentions checksum verification, the core issue remains that the skill is instructing persistent host alteration unrelated to a minimal account-info lookup.
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:$PATH"
This duplicate finding points to the same persistence behavior: installation into a user-controlled directory and PATH modification for future command resolution. Even though the text mentions checksum verification, the core issue remains that the skill is instructing persistent host alteration unrelated to a minimal account-info lookup.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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 instructs the agent to configure API secrets in the host environment via qhkit config set --token or QHKIT_TOKEN. Asking an agent to set persistent credentials for a third-party service exceeds the stated skill purpose and risks secret exposure, misuse, and unintended cross-session persistence.
No suspicious patterns detected.