Security audit
Security checks for vulnerabilities and agentic risk
The skill is a disclosed Qinghu/qhkit integration for generating paid Seedance 2.5 e-commerce videos, with expected but important dependency, credential, and media-upload considerations.
Install only if you intend to use Qinghu/LinkPix qhkit for Seedance 2.5 commerce video generation. Expect the skill to install or run npm packages, ask for a Qinghu API key, store that token through qhkit or environment variables, upload selected product media to the provider, and consume credits only after an explicit generation confirmation. For stricter supply-chain control, pin and review package versions before use.
The manifest description contains very broad trigger keywords spanning generic e-commerce, video generation, advertising, and platform names, which can cause the skill to activate in unrelated conversations. Overbroad auto-invocation increases the chance that users are steered into installing tooling, providing API keys, or uploading assets when they did not explicitly ask for this integration.
The trigger section lists positive activation examples but provides no negative examples or boundary conditions, so an orchestrator may invoke the skill for loosely related requests. In this skill, that matters because activation can lead to environment bootstrapping, package installation, token collection guidance, and external service use, magnifying the impact of misrouting.
The skill instructs use of npx @iqinghu/qhkit without pinning an exact version, which makes execution depend on whatever package version is current at runtime. If the upstream package is compromised, replaced, or introduces breaking behavior, users may execute unreviewed code during a security-sensitive workflow that handles API tokens and media files.
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
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:$PATH"
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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 fallback command npx --yes sharp-cli downloads and executes the latest CLI package on demand without a pinned version. Because this path is triggered during automatic image-processing remediation, it expands the trusted code base and creates a supply-chain risk where arbitrary updated package code may run on the host.
The manifest description embeds English directive text ('Use this skill for ...') alongside Chinese content and mandatory trigger wording, but does not indicate any user language preference or opt-in. This can create a language/locale policy issue because the skill presents a fixed mixed-language interaction pattern rather than offering a language choice.