Topic starter
02/08/2026 9:45 am
TL;DR: Agentic AI security fails when vendors treat prompts as the main control surface and ignore tool execution, memory, and delegated access, Akto reports. Runtime security has to cover live permissions and actions, or unsafe agent behaviour can slip past static guardrails.
Editorial analysis by NHI Mgmt Group, based on content published by Akto: “How to Evaluate AI Security Vendors for Agentic AI Threats”.
Key questions
Q: Why do agentic AI systems need runtime security instead of static guardrails alone?
A: Agentic systems can plan, call tools, and adapt while they are live, so static guardrails cannot reliably predict or contain every harmful sequence.
Q: What are the signs that an AI security vendor is really testing agentic risk?
A: Look for coverage of memory poisoning, unsafe tool chaining, MCP-specific attacks, and adversarial workflows that evolve over time.
Q: What breaks when AI security vendors only scan prompts instead of governing agents?
A: Prompt scanning misses the control surface where agentic risk usually appears: tool choice, memory, permissions, and protocol calls.
Practitioner guidance
- Evaluate agentic threat-model depth Ask vendors to explain how they handle input, execution, and output-layer risk, with explicit coverage of tool misuse, memory poisoning, broken authorization, and MCP connections.
- Test for live interception Require a demonstration of a multi-step attack being blocked in real time, not a report generated after the malicious action has already completed.
- Review red-team coverage Check whether the probe library includes evolving cases for indirect prompt injection, unsafe tool chaining, and agent-to-agent or agent-to-tool escalation paths.
Bottom line: Agentic AI security fails when vendors treat prompts as the main control surface and ignore tool execution, memory, and delegated access.
Glossary terms: Agentic AI Security, MCP Security, Memory Poisoning (ASI06), Runtime Protection
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
This topic was modified 2 days ago by NHI Mgmt Group
02/08/2026 12:38 pm
Agentic AI security is now a delegated-access problem, not just a content-safety problem. The article's strongest message is that control failures emerge when agents can call tools, persist memory, and move through MCP connections with insufficient governance. That is why model scanning alone is structurally incomplete. Practitioners should evaluate security vendors on whether they can govern delegated action across the full agent lifecycle.
A few things that frame the scale:
- Only 44% of organisations have implemented any policies to manage their AI agents, despite 92% agreeing that governing AI agents is critical to enterprise security, according to the 2026 Infrastructure Identity Survey.
A question worth separating out:
Q: Should security teams compare AI-native and legacy AppSec tools differently?
A: Yes. The comparison should focus on whether AI changes coverage, triage quality, and scale of rule creation rather than on branding. Teams should ask whether the tool can handle AI-assisted code, support more languages, and reduce analyst effort without sacrificing precision.
👉 Read our full editorial: Agentic AI vendor evaluations must test runtime control, not prompts
This post was modified 2 days ago by NHI Mgmt Group