Security audit
Ai Eval Plan
Security checks for vulnerabilities and agentic risk
Overview
This skill is a plain planning template for AI evaluation work and does not request sensitive access, persistence, or code execution.
This appears safe to install as a planning aid. It may ask for examples, logs, or failure modes so it can design an eval plan, so avoid sharing sensitive production data unless you intend to use it for evaluation design.
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.