Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed video-watermark removal workflow that uses a third-party CLI and cloud service, with no evidence of hidden or unrelated behavior.
Install only if you trust @iqinghu/qhkit and are comfortable uploading videos to the Qinghu service and using an API token. Prefer reviewing the npm package source/version, avoid unnecessary persistent PATH changes, and use it only for videos you own or are authorized to modify.
The manifest says the skill 'must trigger' whenever a user asks to remove a video watermark and includes broad keywords such as '去水印' and '二次创作'. Without clearer exclusions or narrower context, these phrases can overlap with ordinary conversation and cause unintended activation.
The skill recommends falling back to npx @iqinghu/qhkit <命令> ... without pinning an exact package version. That allows execution of whatever package version is current at install time, increasing supply-chain risk and making builds non-reproducible if the upstream package is compromised or changes behavior.
The same installation guidance persists binaries under the user's home directory and modifies command lookup behavior beyond the current task. Even though the text notes current-shell scope, it also recommends making the change durable via shell startup files, which is a persistence mechanism and therefore a meaningful security concern in an agent skill.
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:$PATH"
The same installation guidance persists binaries under the user's home directory and modifies command lookup behavior beyond the current task. Even though the text notes current-shell scope, it also recommends making the change durable via shell startup files, which is a persistence mechanism and therefore a meaningful security concern in an agent skill.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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 markdown trigger guidance gives one example of eligible requests but does not clarify when the skill should not activate. This leaves the activation condition ambiguous, especially given overlap with adjacent tasks like image watermark removal or subtitle removal.