Security audit
Security checks for vulnerabilities and agentic risk
This skill has a coherent Douyin video-search purpose, but it also tells the agent to install and update external tooling automatically, including unpinned packages and optional PATH persistence.
Install only if you are comfortable letting the agent set up qhkit/Node tooling and configure a Qinghu API token. Prefer reviewing and approving any npm, npx, Node download, PATH, or ~/.bashrc change before it runs, and verify the estimated Qinghu credit cost before paid searches.
The manifest description uses broad mandatory trigger language such as 'must trigger' for loosely related user phrases. This can cause unintended activation of a paid, externally connected tool, increasing the chance of unnecessary data access, costs, or execution in contexts where the user did not clearly request it.
The trigger section lists examples of when to activate but provides no boundaries for when the skill should not run. In a skill that can initiate paid API/tool use, lack of negative activation criteria raises the risk of over-triggering, unintended charges, and unnecessary external calls.
The skill includes extensive instructions to install Node/qhkit, set tokens, modify PATH, and change the local environment well beyond a simple video-search workflow. Even if operationally useful, this expands the attack surface by encouraging code installation and shell/environment changes from within a skill, which could be abused if the dependency or instructions are ever compromised.
The skill instructs use of npx @iqinghu/qhkit without pinning a specific version, which can fetch and execute whatever package version is current at invocation time. That creates supply-chain and reproducibility risk: a compromised or breaking upstream release could be executed in the user's environment unexpectedly.
This duplicate finding points to the same session/persistence behavior: installing binaries under the user's home directory and exporting a modified PATH. In the context of an agent skill, that is dangerous because it normalizes lasting environment changes for a simple search function and could be leveraged by compromised dependencies or future command confusion.
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:$PATH"
This duplicate finding points to the same session/persistence behavior: installing binaries under the user's home directory and exporting a modified PATH. In the context of an agent skill, that is dangerous because it normalizes lasting environment changes for a simple search function and could be leveraged by compromised dependencies or future command confusion.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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.