Topic starter
02/08/2026 11:52 am
TL;DR: RSAC 2026 signals a move beyond prompt injection and data leakage toward agentic AI risks such as workflow compromise, tool misuse, privilege abuse, and multi-step attack chains, according to Straikerai. The core issue is that static-model security assumptions do not hold once agents can act across tools, data, and workflows, so governance must shift to runtime control and visibility.
Editorial analysis by NHI Mgmt Group, based on content published by Straikerai: “What I’m Paying Attention to at RSAC 2026 (If You Care About AI Security)”.
Key questions
Q: What breaks when agentic security systems are governed like chatbots?
A: The control model breaks at runtime.
Q: Why do agentic AI systems increase initial access and privilege abuse risk?
A: Because they can chain valid access into multiple tool calls without needing a human to approve each step.
Q: How do security teams know whether agent guardrails are working?
A: They know guardrails are working when denied tool calls are visible in logs, high-risk paths are blocked consistently, and the agent cannot override policy from inside its own session.
Practitioner guidance
- Map agent authority before expanding deployment Inventory every agent, its connected tools, and the identities or tokens it can use so you know which actions are actually reachable.
- Separate agent permissions from human privileges Do not let agents inherit broad user rights by default.
- Instrument runtime action monitoring Collect telemetry on agent tool calls, approval steps, and cross-system actions so unusual multi-step behaviour can be detected during execution.
Bottom line: Agentic AI changes the security question from what the model generates to what the system is allowed to do across connected tools and workflows.
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
02/08/2026 1:01 pm
Agentic AI security is now an identity governance problem, not just a model-safety problem. Once agents can browse, retrieve, execute, and act, the controlling question becomes who or what is allowed to delegate authority to them and with what limits. That shifts attention from prompt filtering to access scope, session control, and runtime oversight. Practitioners should treat agent permissions as governable identity relationships, not as incidental implementation detail.
A few things that frame the scale:
- Gartner predicts that AI systems will initiate 50% of all service requests by 2030, driven largely by agentic AI.
A question worth separating out:
Q: What should security teams do when agents rely on MCP servers and SaaS connectors?
A: They should treat connectors as privileged trust paths and review them like any other sensitive integration. That means validating authentication, narrowing authorization, and removing unnecessary routes to data or execution. If the connector can reach high-value systems, it must be governed as part of the agent’s effective privilege set.
👉 Read our full editorial: RSAC 2026 exposes the agentic AI security gap teams must close