Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed Chinese-language WeChat article analysis helper and does not show hidden, destructive, persistent, or credential-seeking behavior.
Install this if you want Chinese-language WeChat article diagnostics. Be mindful that giving it a URL may cause that page to be fetched, and verify any health, finance, or other expert-domain content separately because the skill focuses on communication effectiveness, not factual certification.
The trigger list includes broad, generic phrases such as '文章分析' and '运营优化' that can match many ordinary user requests outside the intended public-account/article-diagnosis scope. Overbroad activation can cause the skill to intercept unrelated conversations, increasing the chance of unintended tool use, misleading responses, or inappropriate handling of user content.
SQP-3 applies to all file types and includes language or locale policy violations. This file presents all instructions and examples only in Chinese, with no indication that the skill is region-specific or that users can opt into this language, which may violate a policy requiring language choice or justification.
This markdown file contains user-facing natural language exclusively in Chinese, beginning with the title at L001 and continuing throughout the rubric. Under the policy, forcing a specific language without user opt-in is a locale/language policy violation unless the restriction is clearly documented and justified, which is not present here.
The file title and all instructional content are written exclusively in Chinese, which effectively forces a specific language/locale for use of the skill content. There is no indication that users may choose another language, nor any documented region-specific justification for the restriction.
The skill instructs the agent to fetch arbitrary third-party article URLs but does not warn users that external content will be retrieved and processed. This can create privacy and expectation issues, and in a broader agent environment may increase exposure to untrusted remote content without clear user consent or boundary-setting.
