Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward social-content audit helper that sends the provided note text to a disclosed third-party API and has no hidden local execution or persistence.
Install only if you are comfortable sending the note text you provide to ai.wsdsocial.com with your WSD_API_KEY. Avoid submitting confidential drafts, regulated personal data, secrets, or account credentials unless you trust that provider's handling practices.
The listed triggers include generic terms like "compliance," "audit," "审核," and "moderation," which are broad enough to match many unrelated user requests. The description also mixes example use cases with keyword triggers without clear boundaries or exclusion conditions, making unintended invocation more likely.
The skill sends user-provided note content to an external third-party service at ai.wsdsocial.com, which creates a real data-exposure boundary. If users submit sensitive drafts, personal data, proprietary campaign content, or account-related material, that information leaves the local trust boundary and depends on the external provider's storage, logging, and handling practices.
curl -X POST "https://ai.wsdsocial.com/api/pub/skills/red-note-audit/_tool_87" \
-H "Content-Type: application/json" \
-H "key: ${WSD_API_KEY}" \
-d '{
The natural-language description and trigger phrases embed Chinese terms alongside English, which can implicitly steer interaction toward a specific language/locale without stating user choice. There is no note that the skill supports multiple languages or that Chinese terminology is optional or region-specific.
No suspicious patterns detected.