Security audit
Security checks for vulnerabilities and agentic risk
This parenting advice skill is not malicious, but it should be reviewed because it adds a paid remote API and unpinned payment-tool installation around otherwise simple guidance content.
Review this before installing if you are uncomfortable with paid remote processing of parenting prompts. Confirm the payment agent and endpoint are expected for this marketplace, prefer a pinned reviewed package version, and avoid sending sensitive child or family details unless you trust the provider.
The manifest description lists trigger words like “育儿”, “早教”, “几岁会”, and “亲子游戏”, which are generic phrases likely to appear in ordinary conversation rather than narrowly scoping skill activation. The file does not provide exclusion conditions or negative examples to clarify when the skill should not activate.
The documentation introduces a paid remote API and payment workflow that is not clearly justified by the core parenting-advice behavior described earlier in the skill. This expands the trust boundary to an external service, creates data-sharing and billing risk, and can surprise users or hosting agents with capabilities not obvious from the primary skill purpose.
A payment-agent dependency is context-inappropriate for a parenting advice skill and increases the chance of unnecessary financial operations, external code execution, and user confusion. In this context, monetization plumbing is more dangerous because users expect benign guidance content, not installation of payment tooling.
The skill instructs users to execute npx -y @alipay/agent-payment@latest install, which pulls and runs the latest package version without pinning. That creates a supply-chain risk: a compromised publisher account, malicious new release, or breaking update could execute arbitrary code on the buyer side at install time.
The display name and all user-facing instructions are written in Chinese, but the document does not state that the skill is intended only for Chinese-speaking users or provide an opt-in language/locale choice. Under the policy, forcing a specific language without user choice can be a natural-language policy issue unless the locale restriction is explicit and justified.
No suspicious patterns detected.
