Notifications
Clear all
Topic starter
02/08/2026 12:09 pm
TL;DR: AI agents, prompt injection, tool misuse, memory poisoning, and identity abuse are converging into a broader AI security problem as enterprises deploy autonomous workflows with internal access, according to Akto. The old application-security model breaks because these systems make decisions at runtime and can cascade a single compromised step across enterprise tools.
NHIMG editorial — based on content published by Akto: AI Security Solutions for securing LLMs, AI agents, and enterprise AI in 2026
By the numbers:
- 48% of the firms' cybersecurity professionals have considered Agentic AI the top threat to security.
- While 71% of IT teams have been advised on AI agent data access, only 47% of compliance teams, 39% of legal teams, and 34% of executives have the same visibility.
Questions worth separating out
Q: How should security teams govern AI agents that can access enterprise systems?
A: Security teams should govern AI agents as non-human identities with explicit ownership, scoped privileges, and continuous monitoring.
Q: Why do AI agents complicate traditional IAM and PAM controls?
A: AI agents complicate IAM and PAM because they can make decisions, chain tools, and act faster than human review cycles can respond.
Q: What do security teams get wrong about prompt injection defence?
A: They often assume better blocklists will solve the problem, but obfuscation simply changes the shape of the payload.
Practitioner guidance
- Inventory every AI agent and MCP-connected workflow Map models, tools, APIs, and data sources to a single ownership record so security, IAM, and compliance teams can see which AI actors exist and what they can touch.
- Separate reasoning from execution authority Do not let the same agent both interpret untrusted content and execute sensitive actions without scoped approval boundaries, especially where financial, customer, or administrative systems are involved.
- Apply least privilege to AI agent identities Treat every token, API key, and service credential used by an AI system as a high-risk non-human identity and restrict it to the narrowest tool set and data set required.
What's in the full article
Akto's full blog covers the operational detail this post intentionally leaves for the source:
- A breakdown of AI security solution categories across LLMs, agents, MCP-connected workflows, and runtime protection layers.
- The article's specific examples of prompt injection, tool abuse, memory poisoning, and identity and privilege abuse in enterprise AI.
- Operational guidance on AI-SPM, guardrails, automated red teaming, and continuous monitoring for deployed AI systems.
- The source's own framing of compliance, governance, and runtime enforcement across the AI stack.
👉 Read Akto's analysis of AI security solutions for LLMs and AI agents →
AI security solutions and agentic risk: are your controls keeping up?
Explore further
02/08/2026 1:13 pm
Identity-aware AI security is now a governance discipline, not a point-product feature. The article is right to frame visibility, runtime protection, and continuous monitoring as core requirements because agentic systems blur the line between application behaviour and identity behaviour. Once an AI system can reach internal tools and data, the programme must govern what it can do, when it can do it, and under which identity. Practitioners should treat AI security as part of identity governance, not an overlay on top of it.
A few things that frame the scale:
- 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%), according to AI Agents: The New Attack Surface report.
- Only 52% of companies can track and audit the data their AI agents access, leaving 48% with a complete blind spot for compliance and breach investigation, according to AI Agents: The New Attack Surface report.
A question worth separating out:
Q: How can organisations tell whether AI agent governance is actually working?
A: Look for evidence that agent access is ephemeral, traceable, and constrained at the action level. If the organisation cannot show which runtime acted, what it touched, and which endpoint or command it used, then governance is still too coarse. Effective control produces auditable decisions, not just authentication events.
👉 Read our full editorial: AI security solutions for LLMs and agents need runtime governance
