Security audit
Security checks for vulnerabilities and agentic risk
The skill is mostly a read-only ecommerce research helper, but it repeatedly tells agents to run a mutable npm package at runtime with access to an API key.
Install only if you are comfortable letting the agent run the SocialDataX npm CLI and provide `SOCIALDATAX_API_KEY` for online lookups. Prefer a pinned, reviewed package version or a preinstalled trusted CLI before use; for offline analysis of user-provided product data, no API key or online command should be needed.
The manifest description is entirely in Chinese and presents the skill behavior in that language without indicating that other languages are supported or that the user may choose a preferred language. This can violate language/locale policy when a skill implicitly enforces a specific language without opt-in.
The operational instructions throughout the markdown are provided only in Chinese, with no note that users may select another language or locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.
The skill instructs the agent to execute npx -y socialdatax-skills@latest, which fetches and runs whatever code is currently published under that package name at runtime. This creates a supply-chain risk: a compromised maintainer account, malicious update, or dependency hijack could cause arbitrary code execution in the agent environment, and the presence of an API key in the workflow increases the sensitivity of that execution.
This command also uses npx -y socialdatax-skills@latest, causing unreviewed remote code to be downloaded and executed at the moment the skill is used. In an agent setting, that can lead to arbitrary command execution, data exfiltration, or credential theft if the package or one of its dependencies becomes malicious.
Using npx with an unpinned latest package version exposes the agent to runtime supply-chain compromise. Because the skill is designed for direct CLI execution and may run in environments with network access and configured secrets, exploitation could yield full code execution and access to sensitive environment variables.
This command repeats the same pattern of dynamic execution of the latest package from npm. The danger is not the product-research function itself but the trust boundary crossing: documentation directs the agent to run code whose contents can change without notice after the skill has been published.
The skill again relies on npx -y socialdatax-skills@latest, which is a classic software supply-chain hazard. If the npm package is replaced or updated maliciously, the agent could execute attacker-controlled code before any business logic safeguards in the skill are applied.
This instance has the same risk profile as the other npx ... @latest commands: it enables arbitrary code execution via mutable third-party package resolution at runtime. The context makes it more serious because the skill advertises use in automated agent environments and references a required API key, making secret exposure and broader environment compromise realistic impacts.
No suspicious patterns detected.
