Security audit
Security checks for vulnerabilities and agentic risk
The skill is a coherent read-only ecommerce comparison helper, but it tells agents to run an unpinned npm package at runtime, which should be reviewed before installation.
Review this skill before installing in sensitive environments. If used, pin the SocialDataX npm package to a vetted version, run it with only the required `SOCIALDATAX_API_KEY`, and avoid exposing unrelated secrets or broad filesystem access to the command.
The description is written as a directive in Chinese and does not indicate that users may choose another language or locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified.
The body of the skill, including usage guidance and output expectations, is entirely in Chinese and does not offer an alternative language or ask for user preference. This can amount to a language policy violation because it implicitly constrains interaction to a single language without opt-in or justification.
The skill instructs agents to execute npx -y socialdatax-skills@latest, which pulls and runs the newest package version at execution time without pinning an exact trusted release. This creates a supply-chain risk: if the package or one of its publishing credentials is compromised, agents could automatically execute attacker-controlled code in their local environment.
This command also relies on npx -y socialdatax-skills@latest, causing runtime retrieval and execution of whatever package version is current at that moment. In an agent context, unpinned remote code execution is especially risky because it may run with the agent's filesystem, network, and environment-variable access, including API keys.
The command for the XHS workflow again executes an unpinned package from npm using @latest. Because the skill explicitly promotes direct CLI execution, any future malicious or breaking release could be immediately consumed by downstream users or agents without review.
This is the same supply-chain issue: the skill directs execution of the latest package version from npm at runtime. A compromised package could exfiltrate SOCIALDATAX_API_KEY, modify local files, or perform unauthorized network actions under the agent's privileges.
No suspicious patterns detected.
