Security audit
Security checks for vulnerabilities and agentic risk
This skill is not malicious, but it can post to a user's Knowledge Planet account without a clear final approval step.
Review this skill before installing if you plan to use it for posting. It should only be used when you explicitly intend to operate zsxq.com, and you should require the agent to show the final post content and get your approval immediately before publishing.
The skill explicitly instructs the agent to publish posts directly and says screenshots are not needed, but it does not require an explicit user confirmation immediately before the final publish action. In an automation context, this creates a real risk of unintended or manipulated content being posted under the user's account, especially after the user has already authenticated.
The trigger phrases are broad enough that the skill may be invoked for loosely related requests such as general posting, login help, or content viewing, increasing the chance of unintended activation. Because this skill can perform authenticated actions on a third-party platform, accidental invocation could lead to navigation, login prompting, or posting actions in the wrong context.
This shell script's natural-language comments and echoed output are entirely in Chinese, with no indication that the user can choose another language or that the locale restriction is intentional. The policy explicitly calls for flagging language or locale constraints when they are forced without user opt-in.
This shell script's natural-language comments and echoed messages are entirely in Chinese, with no indication that language choice is optional or configurable. Under the policy for natural-language violations, forcing a specific language without user opt-in should be flagged.
No suspicious patterns detected.
