Security audit
Security checks for vulnerabilities and agentic risk
The skill is mostly coherent for Shopee image generation, but it asks users to share an API key in chat and installs/upgrades unpinned command-line tools with persistent local configuration.
Review before installing. Use a secure local secrets mechanism or environment variable instead of pasting an API key into chat, confirm any paid generation before it runs, and consider pinning package versions or installing qhkit through a controlled process. Be aware that product images and prompts will be uploaded to the qhkit provider for generation.
The skill explicitly tells the agent to ask the user to send an API key in chat and then use it in a shell command. Requesting secrets through conversational channels materially increases the risk of credential disclosure in logs, transcripts, model context, or accidental reuse beyond the intended task.
The description says the skill 'must trigger' whenever a user asks for Shopee product images, main images, detail images, or activity images. This is broad enough to capture many ordinary requests about Shopee visuals, and it does not provide negative examples or boundaries for when another skill should be used instead.
The skill instructs use of npx @iqinghu/qhkit without pinning an exact version, which allows whatever version is current at execution time to be fetched and run. This creates a supply-chain risk: a compromised or breaking upstream release could execute unexpected code in the agent environment.
This duplicated finding points to the same persistence behavior: unpacking binaries into the user's home directory and recommending PATH changes that can survive beyond the immediate task. In agent contexts, persistent tool installation can enable unintended reuse, drift, or abuse by future workflows.
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:$PATH"
This duplicated finding points to the same persistence behavior: unpacking binaries into the user's home directory and recommending PATH changes that can survive beyond the immediate task. In agent contexts, persistent tool installation can enable unintended reuse, drift, or abuse by future workflows.
cd /tmp && curl -fsSLO https://nodejs.org/dist/v22.22.3/node-v22.22.3-linux-x64.tar.xz cd /tmp && curl -fsSL https://nodejs.org/dist/v22.22.3/SHASUMS256.txt | grep ' node-v22.22.3-linux-x64.tar.xz$' | 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 file instructs that installation/configuration failures should be reported to the user in a specific way, and elsewhere notes that CLI messages are already user-facing Chinese. This imposes a Chinese-language interaction pattern without explicit user opt-in or a documented locale-specific justification.
The fallback command npx --yes sharp-cli pulls and executes the latest package version at runtime without version pinning. In a skill that may automatically process user-supplied images, this increases exposure to dependency hijacking or malicious upstream package updates.