Security audit
Security checks for vulnerabilities and agentic risk
This is a transparent Markdown-only WeChat article compliance helper that scans and optionally rewrites user-provided article text, with no hidden execution, persistence, credential access, or network behavior found.
Install this only if you want Chinese WeChat public-account compliance assistance. Review suggested replacements before publishing, especially for political, technical, medical, or commercial wording, and use report-only mode when you do not want the skill to modify a file.
The README presents the skill entirely as Chinese-only and oriented to Chinese-language WeChat compliance checking, with no indication that users can choose language or that the locale limitation is an explicit opt-in. This can violate language/locale policy unless the regional constraint is clearly documented as intentional and justified.
The README describes scanning and report generation but does not clearly warn users that their article content may be automatically rewritten. Because rewriting changes user-authored material, omission of this warning can lead to surprising or unauthorized modification of sensitive publication content, especially in editorial or compliance workflows.
The trigger examples are very broad generic terms like '违规', '敏感词', and '审核', which can cause the skill to activate in conversations that are not actually asking for WeChat article rewriting. Unintended invocation is risky here because the skill performs content scanning and automatic rewriting, potentially altering user text without sufficiently explicit user intent.
The manifest description and body are written entirely in Chinese and describe the skill as operating on WeChat public-account content, but they do not explicitly state that the skill is Chinese-only or offer any language/locale choice. Under the policy, a skill that effectively forces a specific language without user opt-in is a natural-language policy concern unless the locale constraint is clearly documented and justified.
This markdown file is entirely written for a Chinese-language WeChat-publication context and provides prescriptive wording substitutions such as Chinese-only replacements and region-specific publication guidance. There is no indication that users may choose another language/locale or that the locale restriction is optional, which matches the policy's language/locale concern.
No suspicious patterns detected.
