Security audit
Security checks for vulnerabilities and agentic risk
This skill is a small, disclosed task-splitting and role-assignment helper with no evidence of hidden execution, data access, persistence, or exfiltration.
Install this only if a Chinese-language task workflow helper is acceptable for your use case. Review that it is a lightweight classifier/splitter rather than a full multi-agent executor; any actual agent spawning would need to be performed separately by the user or host environment.
The file presents all user-facing instructions and role descriptions exclusively in Chinese, with no indication that language selection is optional or that the skill is intended only for a Chinese-speaking or region-specific context. Under the policy, a skill that effectively enforces a specific language without opt-in can be a natural-language policy violation.
The manifest description and main heading present the skill in Chinese, and the rest of the file continues in that language with no opt-in or alternative language option. This can violate language/locale policy when a skill forces a specific language without user choice or a justified regional constraint.
This manifest uses Chinese-only natural-language text in the description and feature list, which can impose a language choice on users without opt-in. The policy for this review flags skills that force a specific language or locale unless the constraint is explicitly documented and justified.
The module docstring and user-facing interface text indicate the skill is designed for a single language/locale, but the file does not provide any opt-in, fallback, or explanation that it is intentionally region-specific. Under the policy, forcing a specific language without user choice can be a natural-language policy violation.
No suspicious patterns detected.
