Security audit
Multi-Dim Eval Framework Designer
Security checks for vulnerabilities and agentic risk
Overview
This is a documentation-only evaluation-methodology skill with no code execution, credential use, network behavior, or persistence.
Safe to install from a security-behavior standpoint. When using it, only provide evaluation logs, datasets, or internal records that you are allowed to process in your agent environment, and review generated rubrics before relying on them for decisions.
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.