Security audit
Security checks for vulnerabilities and agentic risk
This skill performs a paid video-account search, but it also tells the agent to install or upgrade software and configure credentials on the user's machine, so it needs review before use.
Install only if you are comfortable with qhkit, npm/Node setup, and an iqinghu API token being used for a paid external data service. Prefer a pre-provisioned or sandboxed environment with qhkit already installed, approve paid calls deliberately, and avoid letting the skill modify shell startup files or install latest-version packages automatically unless you trust those sources.
The trigger definition says the skill 'must' be invoked for similar requests and includes broad keyword matching, making activation criteria ambiguous and expansive. Over-broad invocation can cause the agent to enter a paid external-tool workflow unexpectedly, leading to unnecessary data disclosure to third-party services or unintended charges.
The skill’s stated purpose is searching videos within an account, but it additionally directs the agent to install Node, install global packages, configure API credentials, and modify the runtime environment. This materially expands the trust boundary from a narrow data-query action to host-level software deployment and credential handling, which can expose the system to supply-chain compromise, token leakage, and unintended system changes.
These sections instruct the agent to use external package registries, network downloads, mirrors, and local installation flows unrelated to the core search operation. Such bootstrap behavior broadens attack surface substantially and creates an opportunity for supply-chain attacks or execution of unreviewed software in environments where the user only requested a search task.
The skill instructs use of npx @iqinghu/qhkit without pinning an exact version, which permits fetching whatever package version is current at execution time. In a skill that already performs environment bootstrap and package installation, this increases supply-chain risk and makes executions non-reproducible; a compromised or breaking upstream release could execute unexpected code.
This duplicate persistence finding points to the same behavior: extracting software into a user-controlled directory and adjusting PATH for continued availability. In the context of a narrow data-retrieval skill, persistent environment mutation is disproportionate and increases the blast radius of any supply-chain issue or operator mistake.
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:$PATH"
This duplicate persistence finding points to the same behavior: extracting software into a user-controlled directory and adjusting PATH for continued availability. In the context of a narrow data-retrieval skill, persistent environment mutation is disproportionate and increases the blast radius of any supply-chain issue or operator mistake.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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 trigger example '账号内搜索' is quite short and generic, and the section does not provide negative examples or contextual limits for when it applies. In isolation, this may overlap with other account-internal search tasks beyond this specific 视频号 use case.
No suspicious patterns detected.