Security audit
Agent Design Review
Security checks for vulnerabilities and agentic risk
Overview
This skill is a plain markdown guide for reviewing LLM agent designs and does not request execution, credentials, persistence, or broad system access.
This appears safe to install as a review aid. Users should still treat its output as advisory and avoid sharing unnecessary sensitive architecture, credential, or business details when asking for an agent design review.
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.