Notifications
Clear all
Topic starter
05/07/2026 6:53 pm
TL;DR: AI systems are becoming both attack targets and attacker tools as exposed API keys, compromised models, and agentic AI integrations expand the blast radius inside enterprise environments, according to HiddenLayer. The security problem is no longer just model abuse, but identity and access failure across AI deployments, tools, and downstream systems.
NHIMG editorial — based on content published by HiddenLayer: The Expanding AI Cyber Risk Landscape
Questions worth separating out
Q: How should security teams govern AI systems that use API keys and tokens?
A: Treat them as non-human identities with documented ownership, explicit scope, and revocation paths.
Q: Why do exposed AI credentials create such a large security risk?
A: Because exposed credentials turn AI services into legitimate entry points.
Q: What do organisations get wrong about agentic AI risk?
A: They often focus on the model and ignore the permission chain behind it.
Practitioner guidance
- Inventory AI credentials as governed NHIs Build a complete register of API keys, tokens, certificates, and embedded credentials used by AI systems.
- Reduce standing reach on AI toolchains Limit each model, agent, and retrieval pipeline to the minimum systems it needs.
- Segment blast radius across agentic integrations Treat MCP tools, RAG sources, and downstream applications as distinct trust zones.
What's in the full report
HiddenLayer's full research covers the operational detail this post intentionally leaves for the source:
- Examples of how attackers use exposed API keys to access AI services at scale.
- Discussion of agentic AI attack surface growth across MCP tools and RAG pipelines.
- Source examples on supply chain risks, leaked keys, and compromise by extension.
- The vendor's framing of AI deployments as attacker pivot points inside enterprise environments.
👉 Read HiddenLayer's research on the expanding AI cyber risk landscape →
AI cyber risk expansion: what identity teams need to see?
Explore further
05/07/2026 7:14 pm
AI identity risk is becoming an access governance problem, not just a model security problem. The article's core claim is that attackers increasingly abuse exposed keys, model access, and agentic toolchains rather than attacking AI in isolation. That shifts the center of gravity from prompt safety to non-human identity governance, where standing credentials and delegated permissions define the real blast radius. Practitioners should treat AI systems as governed identities with measurable access scope, not as abstract software features.
A few things that frame the scale:
- 72% of organisations have experienced or suspect they have experienced a breach of non-human identities, with 46% confirmed and 26% suspected, according to The 2024 ESG Report: Managing Non-Human Identities.
- Two-thirds of enterprises have endured a successful cyberattack resulting from compromised non-human identities, and a quarter have faced multiple attacks.
A question worth separating out:
Q: How can teams reduce the damage if an AI system is compromised?
A: Limit the AI system's delegated access, isolate tool connections, and separate sensitive workflows into different trust zones. The goal is to prevent one compromised model or agent from exposing unrelated datasets, applications, or operational actions. Identity scope should be narrow enough that a single failure cannot become enterprise-wide exposure.
👉 Read our full editorial: AI cyber risk is expanding faster than enterprise controls
