Security audit
Security checks for vulnerabilities and agentic risk
The skill appears to do the claimed Douyin metadata lookup, but it also directs agents to install tooling and configure persistent API credentials on the user's machine.
Review before installing. Use this only if you are comfortable with the agent installing or upgrading Node/qhkit, running an external paid data tool, and configuring a qhkit API token locally. Prefer preinstalling vetted dependencies yourself and providing credentials through a controlled secret mechanism.
The trigger description includes broad language like 'or similar needs must trigger,' which can cause the skill to activate on ambiguous requests. In context, that matters because this skill is capable of leading the agent into installation, configuration, and credential-handling flows, so over-triggering increases the chance of unnecessary risky actions.
The example trigger phrases are underspecified and do not require enough context, such as a valid Douyin link or confirmation that only basic metadata is wanted. Because the skill includes invasive setup and paid-call behavior, broad invocation criteria make accidental activation more dangerous than in a read-only local skill.
The skill goes far beyond its stated purpose of retrieving Douyin video metadata by directing the agent to install Node, install packages, modify PATH, and bootstrap tooling on the host. This expands the attack surface from a narrow data fetch into host-environment modification and arbitrary software installation, which is risky even if framed as convenience.
The skill instructs use of npx @iqinghu/qhkit without pinning a specific version, which allows whatever package version is current at execution time to be fetched and run. In a security-sensitive agent context, unpinned remote tooling increases supply-chain risk and makes behavior non-reproducible.
This duplicate finding reflects the same persistent host-modification behavior: unpacking software into the user's home directory and exporting a modified PATH. Even with checksum verification, the issue is not just integrity of the download but the unnecessary persistence and scope expansion for a simple metadata retrieval 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:$PATH"
This duplicate finding reflects the same persistent host-modification behavior: unpacking software into the user's home directory and exporting a modified PATH. Even with checksum verification, the issue is not just integrity of the download but the unnecessary persistence and scope expansion for a simple metadata retrieval skill.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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 skill instructs configuration of authentication secrets (qhkit config set --token and environment variables) in the host environment. Asking an agent to set persistent secrets for a narrowly scoped metadata lookup unnecessarily exposes credentials to leakage, misuse by other tools, or persistence beyond the user's intended action.
No suspicious patterns detected.