Security audit
Agent-Friendly Design
Security checks for vulnerabilities and agentic risk
Overview
This is a markdown-only design guide for making websites easier for AI agents to use, with no executable code or hidden runtime behavior.
Safe to install as guidance. Before applying its crawler, llms.txt, API, MCP, or automation-access recommendations, decide which parts of your site should be machine-readable and keep sensitive or private areas protected by real authentication and authorization.
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.