About this episode

Richard Campbell discusses the security risks associated with AI agents and prompt injection with Niall Merrigan.

AI Agents can be powerful tools for an organization - but are they a security risk? Richard talks to Niall Merrigan about his experiences dealing with the various ways that LLMs can be attacked, starting with prompt injection. While some attacks are humorous, others can be very serious, especially in the context of agents, where the right prompt can cause an agent to use its capabilities to access or affect data outside its expected behavior. This has already led to several well-publicized CVEs, including the ServiceNow Privilege Escalation advisory. New tools have emerged to help restrict prompts and keep agents on task - but as with all things security, this is another set of tools you need to get familiar with!

More episodes of RunAs Radio

• The Life and Death of Microsoft Deployment Toolkit with Michael Niehaus · April 21, 2026 · 39 min
• Internal Corporate Communications in 2026 with Emily Mancini · April 14, 2026 · 35 min
• My Home Lab · March 31, 2026 · 10 min
• Unified Tenant Management with Nik Charlebois-Laprade · March 24, 2026 · 34 min
• Sustainable AI with Darshna Shah · March 17, 2026 · 43 min
• SQL Server in 2026 with Bob Ward · March 10, 2026 · 40 min

Explore listener stats, chart rankings, contacts and more on the RunAs Radio podcast page.