Security audit
Security checks for vulnerabilities and agentic risk
The skill is mostly a read-only product copywriting helper, but it asks agents to run an unpinned npm package at use time, which should be reviewed before installation.
Install only if you are comfortable letting the agent run the SocialDataX npm CLI locally with your environment, including access to `SOCIALDATAX_API_KEY`. Prefer a pinned, reviewed package version or a preinstalled trusted CLI before use, and keep the API key scoped to this service.
The manifest description is entirely written as an instruction for Chinese-language use and does not indicate that other languages are supported or that the user can opt into Chinese. Under the policy, forcing a specific language without user choice is a natural-language policy violation unless the locale restriction is clearly documented and justified.
The primary usage description is presented only in Chinese and frames the skill's behavior without offering a language selection mechanism. Because no justified region- or compliance-specific reason is given for restricting the skill to Chinese, this is a language policy concern.
The skill instructs agents to execute npx -y socialdatax-skills@latest, which fetches and runs the newest package version at runtime rather than a reviewed, pinned release. This creates a supply-chain risk: if the package or one of its publish paths is compromised, the agent may execute attacker-controlled code with the agent's local permissions and access to environment variables such as SOCIALDATAX_API_KEY.
This command repeats the same unsafe pattern of invoking npx with @latest, causing unreviewed code to be downloaded and executed on demand. In an agent setting, that materially increases exposure to package compromise, typosquat replacement, or malicious upstream changes that could exfiltrate secrets or run arbitrary commands.
The documented runtime dependency is not version-pinned and is executed directly via npx, so every invocation may run newly published code without review. Because this skill is designed for CLI use and references an API key, compromise of the package could lead to arbitrary code execution and credential exposure in the user's environment.
By instructing agents to run npx -y socialdatax-skills@latest, the skill delegates trust to the current npm registry state instead of a vetted artifact. That is dangerous because a compromised or malicious package update can execute arbitrary code immediately when the skill is used.
This finding reflects another direct execution path for an unpinned npm package. Since the skill is explicitly operational and not merely descriptive, users or agents following the instructions would run code whose contents can change over time, creating a realistic supply-chain execution risk.
The same unpinned npx pattern appears here, preserving the risk that the skill will execute whatever code is most recently published under that package name. In practice, this can enable remote code execution and theft of local secrets if the npm supply chain is abused.
No suspicious patterns detected.
