Topic starter
02/08/2026 12:28 pm
TL;DR: AI application security must now cover prompt injection, data poisoning, model theft, and other AI-specific threats that conventional AppSec often misses, according to Akto. The governance challenge is no longer just securing code and APIs, but controlling model behavior, data flows, and agent interactions across the full lifecycle.
Editorial analysis by NHI Mgmt Group, based on content published by Akto: “AI Application Security: A Modern Approach to Safer AI Systems”.
Key questions
Q: How should security teams govern AI models that can call tools and access data?
A: Security teams should govern AI models as non-human identities with named owners, limited scope, short-lived credentials, and continuous authorization.
Q: Why do GenAI apps and agents need controls beyond AppSec and cloud security?
A: Because the AI system turns language, files, retrieved context, and tool access into behaviour.
Q: What are the signs that an AI agent is being manipulated into unauthorized actions?
A: Warning signs include unexpected data retrieval, unusual tool calls, changes in agent decisions after hostile or extreme inputs, and outputs that reflect hidden instructions rather than the user’s request.
Practitioner guidance
- Define explicit agent authorisation scopes Document which data sources, tools, and workflows each AI agent may access, and deny everything outside that task scope by default.
- Add model and dataset integrity checks Validate training inputs, fine-tuning data, and model artefacts before promotion so tampering and poisoning are detected before deployment.
- Instrument prompt and output monitoring Log high-risk prompts, unusual tool calls, and suspicious outputs so security teams can investigate manipulation attempts and unsafe behaviour.
Bottom line: AI application security is increasingly about controlling model behaviour, agent authority, and data pathways, not only finding code flaws.
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
02/08/2026 1:26 pm
AI application security is now a governance problem, not just a testing problem. Traditional AppSec can still find familiar software defects, but it cannot by itself govern model behaviour, tool use, or delegated agent actions. The shift described in this article is structural: AI systems introduce a control plane that spans data, model, and runtime authority, which means security teams must manage what the system is allowed to do, not just what code it runs. The practitioner takeaway is that governance has to move upstream into design and authorisation.
A few things that frame the scale:
- 67% of organisations still rely heavily on static credentials despite the risks they pose to agentic AI deployments, according to the 2026 Infrastructure Identity Survey.
- 53% of security leaders expect AI to run major portions of their infrastructure autonomously within the next three years, according to the 2026 Infrastructure Identity Survey.
A question worth separating out:
Q: When should organisations prioritise AI governance over point-in-time testing?
A: They should prioritise governance as soon as models or agents begin influencing decisions, accessing sensitive data, or invoking tools. Point-in-time testing can validate a release, but it cannot control what changes during runtime, after model updates, or when new inputs reshape system behaviour.
👉 Read our full editorial: AI application security is shifting toward agent and model governance