Security audit
AI角色互动对话设计技能
Security checks for vulnerabilities and agentic risk
Overview
This skill is a self-contained classroom dialogue-writing guide and does not ask for risky access or hidden actions.
Reasonable to install for generating classroom dialogue materials. Review generated math explanations before using them in teaching, and avoid including student personal data in prompts unless your normal privacy controls allow it.
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.