Our Resources
Mitigating Vector and Embedding Weaknesses
OWASP released a new version of the Top 10 LLM risks in November 2024, adding a new category: Vector and Embedding Weaknesses. RAG pipelines...
Rolling out M365 Copilot? Beware of Overshared Content
Enterprises are rolling out Microsoft 365 (M365) Copilot for productivity gains, helping in variety of tasks—summarizing emails or meetings,...
The State of Security Observability in Agentic Platforms
As AI agents move from experiments to production in enterprises, security observability has become critical. Unlike traditional software sys...
Detecting XPIA (Cross Prompt Injection Attacks)
Detecting XPIA (Cross Prompt Injection Attacks) Cross Prompt Injection Attacks (XPIA) are in the news. One recent case is EchoLeak M365 copi...
Monitoring Agentic Tool Use with Observability Data
Over the past few months, we’ve witnessed a growing concern in the agentic AI space: agents going rogue and executing harmful actions using ...
Where Ackuity Fits Into GenAI Security
Where Ackuity Fits Into GenAI Security GenAI security is complex and evolving, and so are the solutions that address it. While some GenAI se...
Top 10 Gen AI Security Risks
At the Prompt level 1. Prompt injection LLMs have guardrails to filter out specific content. Also, when enterprises build their GenAI applic...