Security audit
experience-model-builder
Security checks for vulnerabilities and agentic risk
Overview
This is a simple instruction-only skill for turning user-provided experiences into reusable structured models, with no code execution or hidden access.
This skill is reasonable to install for drafting structured summaries of practices or methods. Users should still avoid pasting secrets, sensitive personal information, or proprietary internal processes unless they are comfortable with that content being included in the generated model.
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.