Security audit
Systems Thinking by 小钳
Security checks for vulnerabilities and agentic risk
Overview
This is a plain instructional systems-thinking skill with no code execution, credential access, persistence, or external data flow.
Safe to install as an educational thinking framework. It should only influence how the agent analyzes complex systems; it does not need tool access, credentials, or background execution.
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.