Notifications
Clear all
Topic starter
02/08/2026 12:15 pm
TL;DR: AI security testing tools now have to validate model, API, and agent behaviour across training and runtime because prompt injection, tool misuse, and shadow endpoints create failure modes that traditional testing misses, according to Akto. The real governance gap is that security testing often checks outputs while attackers target delegated access, tool chains, and MCP-connected workflows.
NHIMG editorial — based on content published by Akto: Best AI Security Testing Tools to Protect Your AI Systems
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: How should security teams test AI agents that can call tools and APIs?
A: They should test the agent's actual execution paths, not just its text responses.
Q: Why do MCP-based agents create new access control risks for IAM teams?
A: Because they turn a model from a text generator into a delegated actor that can reach real systems.
Q: What breaks when AI security testing ignores undocumented endpoints?
A: Coverage fails at the exact point where shadow AI often lives.
Practitioner guidance
- Inventory every AI endpoint and agent connection Build a live register of LLM APIs, agent endpoints, MCP servers, and undocumented shadow interfaces before you attempt coverage testing.
- Test authorisation at the tool layer Simulate prompt injection, tool misuse, and instruction hijacking against the exact actions an agent can take.
- Link AI red-teaming to IAM and PAM controls Translate every successful attack simulation into a control change such as tighter scopes, shorter-lived tokens, stronger approval gates, or revocation of unused access.
What's in the full article
Akto's full blog covers the operational detail this post intentionally leaves for the source:
- Step-by-step comparisons of AI security testing tool categories, including where each fits in development and runtime.
- Vendor-by-vendor examples of adversarial attack libraries, red-teaming platforms, and monitoring tools for AI workflows.
- Operational guidance on integrating AI testing into CI/CD, SOC workflows, and governance reporting.
- Detailed capability descriptions for MCP workflows, agent endpoints, and AI-to-API monitoring.
👉 Read Akto's guide to the best AI security testing tools for agents and MCP →
AI security testing tools for agents and MCPs: are controls keeping up?
Explore further
02/08/2026 1:17 pm
AI security testing is now an identity governance problem, not just a model quality problem. Once an agent can call tools, retrieve data, or trigger workflows, the meaningful security question becomes who or what is authorised to act. That shifts testing from content validation to delegated access validation. Organisations should therefore test AI behaviour as part of IAM and NHI governance, not as a standalone model exercise.
A question worth separating out:
Q: What should organisations do when AI testing finds unsafe tool behaviour?
A: Treat the result as an access-control issue, not only a model defect. Organisations should narrow scopes, shorten token lifetimes, add approval checks for high-risk actions, and remove unused connectors. The goal is to make the same unsafe action impossible to repeat after remediation.
👉 Read our full editorial: AI security testing tools need identity-aware controls for agents and MCP
