Agentsafelabs
agentsafelabs.com
Actively hiring
Cybersecurity AI
Penetration Testing
AI Safety & Alignment
As featured in
Follow
Overview
News
Salaries
Products
People
Growth
Offices
Financials
News
Prompt Injection Is Not a Chatbot Problem: How the Attack Surface Changes When Your LLM Has Tools
The prompt injection defenses built for chatbots do not work for agents. Here is why the attack surface changes fundamentally when your LLM can call tools, read documents, and take actions.
Read more
Report
The OWASP Agentic Security Initiative Top 10: A Practical Developer Guide for LangChain and CrewAI
OWASP formalized ASI01-ASI10 - the first structured vulnerability taxonomy for AI agents. What each category means in practice, with real safelabs-eval test results for every category. For LangChain and CrewAI developers.
Read more
Report
GitHub - AgentSafeLabs/safelabs-eval: OWASP ASI-aligned red-teaming and evaluation framework for AI agents
OWASP ASI-aligned red-teaming and evaluation framework for AI agents - AgentSafeLabs/safelabs-eval
Read more
Report