Notifications
Clear all
Topic starter
02/08/2026 11:46 am
TL;DR: GenAI systems now sit between user intent, internal data, tools, and execution, which makes their security risks emerge from context handling, retrieval, and action-taking rather than isolated code flaws, according to Akto. The governance problem is no longer model quality alone, but whether enterprises can constrain behaviour, validate outputs, and track who or what is acting.
NHIMG editorial — based on content published by Akto: GenAI Security Risks: Top Threats, Examples & Mitigation Strategies (2026 Guide)
By the numbers:
- 80% of organisations report their AI agents have already performed actions beyond their intended scope, including accessing unauthorised systems (39%), inappropriately sharing sensitive data (31%), and revealing access credentials (23%).
- 96% of technology professionals identify AI agents as a growing security threat, and 66% believe this risk is immediate.
Questions worth separating out
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.
Q: Why do endpoint agentic AI tools create more governance risk than chat-only GenAI?
A: Endpoint agentic AI can act inside a user’s session, move data, and trigger downstream actions, which expands the effective privilege boundary.
Q: How do security teams know if AI governance is working?
A: Look for evidence that access decisions are reviewable, permissions are revocable, and exceptions are not becoming permanent.
Practitioner guidance
- Implement context-bound access rules Define which prompts, documents, and retrieval sources can enter each GenAI workflow, and separate sensitive context from general-purpose model interactions.
- Treat AI agents as governed non-human identities Assign explicit ownership, approval boundaries, and revocation logic to every agent that can call tools or manipulate records.
- Validate outputs before downstream execution Block direct handoff from model output to business-critical systems unless a policy or human review step confirms the action is safe.
What's in the full article
Akto's full guide covers the operational detail this post intentionally leaves for the source:
- Risk-by-risk mitigation guidance for prompt injection, data leakage, retrieval abuse, and hallucination handling
- Practical examples of how GenAI failures surface in enterprise workflows, including assistants, agents, and SaaS integrations
- Checklist-style controls for visibility, permission scoping, and validation across production AI systems
- The article’s framing of Shadow AI, AI supply chain risk, and adversarial testing as separate governance problems
👉 Read Akto's guide to GenAI security risks, examples, and mitigation strategies →
GenAI security risks in 2026: where are the control gaps?
Explore further
02/08/2026 12:56 pm
GenAI security risks are becoming an identity problem before they are a model problem. Once AI systems can retrieve data, call tools, and trigger workflows, the central governance question becomes who or what is authorised to act. That is why IAM and PAM teams cannot treat GenAI as a separate domain. The control gap sits at the point where machine behaviour acquires operational authority, so identity governance must extend into AI runtime decisions.
A question worth separating out:
Q: What should organisations do when GenAI is embedded in code and workflows?
A: Apply secure SDLC and third-party dependency controls to AI outputs, including review for bugs, secrets, prompt-injection artifacts, and unsafe API use. AI-assisted code is not exempt from normal engineering governance. The practical standard is the same as any external input: inspect, test, approve, and monitor before it reaches production.
👉 Read our full editorial: GenAI security risks in 2026 are really identity and control gaps
