EPISODE · Apr 8, 2026 · 37 MIN
Securing AI Agents with Niall Merrigan
from RunAs Radio · host Niall Merrigan, Richard Campbell
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!LinksAI Recommendation PoisoningDetecting Prompt Injection AttacksMark Russinovich Crescendo Multi-Turn LLM Jailbreak AttackCross-Site Scripting (XSS)Cameron Mattis LinkedInPrivilege Escalation in ServiceNow AI PlatformAzure AI Content Safety Prompt ShieldsTask AdherenceSimon Willison's Lethal TrifectaMicrosoft Agent 365PyRITOWASP Securing Agentic Applications GuideRecorded February 16, 2026
What this episode covers
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!
NOW PLAYING
Securing AI Agents with Niall Merrigan
No transcript for this episode yet