Resources & References

Curated links to security research, incident analyses, and hardening guides.

📚

Security Audits & Academic Papers

Academic papers analyzing vulnerabilities in agentic AI deployments, including Clawdbot case studies.

Research on prompt injection techniques specifically targeting AI agents with tool access.

🔍

Detailed breakdown of the Clawdbot incident timeline and security implications.

Analysis of systemic security issues across agentic AI deployments.

Technical analysis of how default configurations led to mass exposures.

🛠️

Fast, template-based vulnerability scanner. Includes templates for exposed agent endpoints and misconfigurations.

Official visual developer tool for testing and debugging MCP servers and their integrations.

LLM vulnerability scanner for testing resilience against prompt injection, data leakage, and hallucination.

Get weekly security updates, new research, and hardening guides delivered to your inbox.

Know a resource that should be listed here? Submit it