Security audit
Security checks for vulnerabilities and agentic risk
This skill locally converts a user-provided article into Chinese social-platform draft formats and does not show hidden posting, network, persistence, or data-exfiltration behavior.
Install this if you want local Chinese social-media draft generation from text you provide. Be aware that the interface and generated copy are Chinese-focused, and review drafts manually before posting because the skill does not check current platform rules or publish for you.
The tagline is entirely in Chinese and describes the skill as producing drafts for Chinese platforms, which indicates a language-specific behavior. The manifest does not state that the user can choose another language or that Chinese output is optional, so this appears to impose a locale/language constraint without explicit opt-in.
The skill’s natural-language description, invocation examples, workflow, and output guidance are written entirely in Chinese, which effectively forces a specific language/locale for use. The policy allows locale constraints only when users are given a choice or the constraint is clearly justified as region-specific, neither of which is stated here.
The file includes its top-level description and usage guidance entirely in Chinese, and later user-facing output and errors are also Chinese-only. Because the skill does not offer language selection or state that it is intentionally limited to a Chinese-only audience, this is a natural-language locale policy concern under the language/locale rule.
No suspicious patterns detected.
