Notifications
Clear all
Topic starter
02/08/2026 11:52 am
TL;DR: RSAC 2026 sessions point to a shift from prompt injection and data leakage toward agentic AI risks such as workflow compromise, tool misuse, privilege abuse, and multi-step attack chains, according to Straiker. The core problem is that conventional model security assumes static behaviour, while agentic systems act across tools, data, and workflows in ways IAM and runtime controls must now govern.
NHIMG editorial — based on content published by Straikerai: What I’m Paying Attention to at RSAC 2026 (If You Care About AI Security)
By the numbers:
- 80% of organisations report their AI agents have already performed actions beyond their intended scope, including accessing unauthorised systems, inappropriately sharing sensitive data, and revealing access credentials.
Questions worth separating out
Q: How should security teams govern agentic AI as it moves into production?
A: Security teams should govern agentic AI as a class of non-human identity, not as a generic application feature.
Q: Why do AI agents create a different risk model than chatbots?
A: AI agents can act, not just generate.
Q: What breaks when AI agents are given broad inherited permissions?
A: Broad inherited permissions break the assumption that access is tied to a narrow business need.
Practitioner guidance
- Define agent identity ownership Assign a human owner, a business purpose, and an explicit entitlement set to every agent before it is allowed to interact with tools, data, or workflows.
- Constrain MCP and tool scopes Map every MCP connection, SaaS token, and API credential used by AI systems, then reduce each one to the narrowest task-scoped permission set possible.
- Monitor agent behaviour at runtime Collect logs that show what the agent accessed, which tools it called, what data it retrieved, and which action it completed.
What's in the full article
Straiker's full blog covers the session-level detail this post intentionally leaves for the source:
- Speaker-by-speaker RSAC session breakdowns, including the specific talks the author expects to shape the agentic AI agenda
- Practical examples of how prompt injection, tool misuse, and MCP risk chain into real attack paths
- The author's reasoning for why AI desktop apps, coding agents, and autonomous workflows are now the primary attack surface
- A day-by-day list of sessions and the operational themes each one is intended to surface
👉 Read Straiker's RSAC 2026 agentic AI security session recommendations →
Agentic AI security at RSAC 2026: what should teams prioritise now?
Explore further
02/08/2026 1:01 pm
Agentic AI is becoming an identity governance problem, not just a model safety problem. The article is right to move the discussion from prompt content to what agents can actually do. Once an AI system can browse, call tools, and persist across sessions, governance has to account for authority, scope, and lifecycle. That is where NHI governance and PAM patterns overlap with AI security. Practitioner conclusion: teams should govern agent permissions the same way they govern other high-risk machine identities.
A question worth separating out:
Q: Who is accountable when an AI agent accesses sensitive data it was not meant to use?
A: Accountability sits with the team that approved the agent, its connectors, and its policy boundaries, not with the runtime behaviour alone. Organisations need ownership for intent, permissions, monitoring, and validation so they can prove whether the agent stayed inside its approved purpose. Without that, audit and regulatory response become retrospective guesswork.
👉 Read our full editorial: RSAC 2026 exposes the agentic AI security gap teams must close
