Notifications
Clear all
Topic starter
02/08/2026 11:48 am
TL;DR: Enterprise AI systems now operate as copilots, chatbots, workflows, and agents that can call tools, retrieve context, and trigger actions, so traditional AppSec boundaries no longer map cleanly to exploitability, according to Terra. The security issue is no longer bad output, but manipulated behaviour that can become unauthorised action across the AI stack.
NHIMG editorial — based on content published by terra: Enterprise AI Security: What Security Leaders Need to Know About AI Applications, Copilots, and Agents
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%).
Questions worth separating out
Q: What breaks when AI agents are treated like standard human users?
A: You lose visibility into effective permissions, expected behaviour, and real blast radius.
Q: Why do AI agents create a governance problem for IAM teams?
A: AI agents create a governance problem because they authenticate and act as autonomous software entities with tool access.
Q: How do security teams know whether AI exploitability is actually being reduced?
A: Look for evidence that manipulated prompts no longer translate into tool calls, data exposure, or workflow actions.
Practitioner guidance
- Map AI execution paths end to end Document how prompts, retrieval layers, memory stores, tools, and downstream workflows connect, then identify where a manipulated input can become an unauthorised action.
- Separate model access from action authority Treat model output as advisory unless a separately enforced control authorises the next step.
- Apply continuous validation to AI changes Re-test AI systems whenever prompts, integrations, models, or permissions change, because each update can create a new exploit path.
What's in the full article
terra's full article covers the operational detail this post intentionally leaves for the source:
- Terra’s testing approach for validating exploitability across input, retrieval, memory, tools, and downstream workflows.
- Examples of AI vulnerabilities observed in production environments, including prompt injection, tenant boundary issues, and workflow abuse.
- How the vendor frames continuous penetration testing for AI-enabled systems versus one-off model assessment.
- The article’s discussion of what security leaders should ask before AI is allowed to act autonomously.
👉 Read terra's analysis of enterprise AI application security and exploitability →
AI copilots and agents: are your controls keeping up?
Explore further
02/08/2026 12:58 pm
AI exploitability, not model correctness, is the security problem. The article is right to separate unsafe output from unsafe outcome. Enterprise AI risk emerges when manipulated context is converted into data access, tool execution, or workflow action. That makes the issue an authorization and governance problem as much as a model risk problem. Practitioners should treat exploitability as the primary control objective.
A question worth separating out:
Q: What frameworks should organisations use to assess agentic AI risk?
A: Use OWASP Agentic AI Top 10 for threat modelling, OWASP NHI guidance for credential and privilege governance, and Zero Trust principles for continuous verification of tools and identities. Together, they help teams evaluate agent behaviour, access boundaries, and trust at runtime instead of only at onboarding.
👉 Read our full editorial: Enterprise AI security needs continuous testing across the full stack
