Security audit
Security checks for vulnerabilities and agentic risk
The skill is mostly a TikTok search integration, but it also tells agents to install or upgrade runtime software and persist API credentials without clear per-action user control.
Review before installing. This skill may be reasonable if you trust qhkit and want Qinghu TikTok data access, but install dependencies and configure the API token yourself where possible, avoid running latest/unpinned packages in privileged environments, and confirm any paid call before use.
The phrase '或提出同类需求时必须触发' makes the trigger boundary vague and expansive. Overbroad activation can cause the skill to run in unintended contexts, increasing the chance that the agent follows the skill's installation, auth, or paid-tool instructions when a narrower or safer response would have been appropriate.
For a skill whose declared purpose is TikTok search, the file contains broad environment bootstrap instructions: installing Node, installing global packages, downloading archives, modifying PATH, and handling mirrors. This expands the skill from a narrow data query into general system modification, increasing attack surface and enabling persistent changes unrelated to the user's immediate request.
The skill instructs use of npx @iqinghu/qhkit without pinning an exact version, which permits execution of whatever package version is current at invocation time. In a privileged agent environment, this creates supply-chain risk and makes behavior non-reproducible, especially because the same skill also encourages installation and credential configuration.
This duplicated finding describes the same persistent installation behavior: writing binaries under the user's home directory and changing PATH for subsequent shells. In context, this is more dangerous because the skill is nominally just for TikTok search, so persistent environment mutation is unnecessary and disproportionate to purpose.
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:$PATH"
This duplicated finding describes the same persistent installation behavior: writing binaries under the user's home directory and changing PATH for subsequent shells. In context, this is more dangerous because the skill is nominally just for TikTok search, so persistent environment mutation is unnecessary and disproportionate to purpose.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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 set persistent authentication credentials via qhkit config set --token <密钥> --env prod or environment variables. A search-only skill should not direct an agent to alter long-lived auth state, because this can store secrets on disk or in process environments and broaden access beyond the current task.
No suspicious patterns detected.