Security audit
Security checks for vulnerabilities and agentic risk
This skill is for a real script-generation workflow, but it gives the agent broad authority to install and update command-line tooling and handle service tokens with limited user control.
Install only if you are comfortable letting the agent install or update npm tooling, configure qhkit credentials, and upload referenced product media to the qhkit/iqinghu service. Prefer a preinstalled, pinned qhkit version and provide tokens through a secure secret mechanism rather than having the agent persist or troubleshoot them broadly.
The trigger definition says the skill 'must' fire for broad, common requests related to ad copy and scripts. Overbroad mandatory triggering can cause unintended invocation of external tooling, increasing the chance that installation steps, network access, or credential flows are activated when a simple local response would suffice.
The file is written to operate in Chinese and instructs use of Chinese output/content conventions, but it does not state that the skill is China-specific only or give users any opt-in or alternative language option. Per policy, forcing a specific language/locale without user choice is a natural-language policy concern.
The skill goes far beyond script generation and instructs the agent to install Node.js, globally install and upgrade a CLI, and modify the execution environment. Those are privileged, system-modifying actions not necessary for a text-generation skill and expand the attack surface through package installation, PATH changes, and persistent tooling changes.
The skill instructs use of npx @iqinghu/qhkit without a pinned version, allowing whatever version is current at execution time to be fetched and run. That creates a supply-chain risk and makes behavior non-reproducible, especially since this skill already encourages installing and executing external tooling.
This duplicate finding reflects the same persistence behavior: installing a runtime under the user's home directory and exporting a modified PATH. In the context of a content-generation skill, that is an unnecessary environment mutation that can outlive the task and facilitate further unreviewed command execution.
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:$PATH"
This duplicate finding reflects the same persistence behavior: installing a runtime under the user's home directory and exporting a modified PATH. In the context of a content-generation skill, that is an unnecessary environment mutation that can outlive the task and facilitate further unreviewed command execution.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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 directs the agent to obtain, set, and troubleshoot API tokens and environment variables. That gives a script-writing skill credential-handling responsibilities it does not need, increasing the risk of secret exposure, misuse, and cross-service confusion between domestic and international endpoints.