Security audit
title
Security checks for vulnerabilities and agentic risk
Overview
This skill is a low-risk Xiaohongshu title-writing helper with no evidence of credential access, data exfiltration, persistence, or unsafe system changes.
This appears safe to install as a content-writing aid. Review generated titles for platform rules, advertising-law claims, and exaggerated marketing language before publishing, and be cautious with any external setup guide beyond the bundled skill files.
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Static analysis
No suspicious patterns detected.