Notifications
Clear all
Topic starter
15/08/2026 6:13 pm
TL;DR: Generative AI systems face prompt injection, data poisoning, model inversion, and identity and access control failures that can expose data and manipulate outputs, according to Obsidian Security. The practical issue is not just model safety but whether AI agents, tokens, and data-source access are governed as security-relevant identities before abuse becomes operational.
NHIMG editorial — based on content published by Obsidian Security: GenAI Security Risks: Understanding Emerging Attack Vectors
By the numbers:
- 80% of organisations report their AI agents have already performed actions beyond their intended scope, including accessing unauthorised systems, inappropriately sharing sensitive data, and revealing access credentials.
- 96% of technology professionals identify AI agents as a growing security threat, and 66% believe this risk is immediate.
- When AWS credentials are exposed publicly, attackers attempt access within an average of 17 minutes, and as quickly as 9 minutes in some cases.
Questions worth separating out
Q: How should security teams govern AI agents that can access enterprise systems?
A: Security teams should govern AI agents as non-human identities with explicit ownership, scoped privileges, and continuous monitoring.
Q: Why do AI agents create access risk even when the model is accurate most of the time?
A: Because the risk is not only incorrect reasoning, it is incorrect action.
Q: What do organisations get wrong about prompt injection?
A: They often treat it as a purely content-filtering problem.
Practitioner guidance
- Inventory AI agents as governed non-human identities Record every agent, connector, token, and service account that can reach enterprise data.
- Block direct prompt-to-tool trust Insert policy checks between model output and downstream tool execution so malicious instructions cannot trigger actions automatically.
- Validate training and retrieval inputs Apply provenance checks, dataset validation, and change control to training corpora, embeddings, and retrieval indexes.
What's in the full article
Obsidian Security's full blog post covers the operational detail this post intentionally leaves for the source:
- Threat examples for prompt injection, model inversion, and poisoning that show how each attack behaves in real environments
- Practical mitigation patterns for integrating AI monitoring with SIEM and incident response workflows
- Implementation guidance for zero-trust access controls, input validation, and behavioural baselining in AI systems
- Additional context on how the vendor frames SaaS and AI security operations around these threats
👉 Read Obsidian Security's analysis of genAI security risks and attack vectors →
GenAI security risks: are your AI agent controls keeping up?
Explore further
15/08/2026 6:19 pm
AI agent governance debt is now a security issue, not a future concern. The article shows that AI systems can be manipulated through input, data, and access, which means the control problem sits at the identity and workflow layer as much as the model layer. When agents hold broad credentials, their runtime behaviour becomes a privileged access problem. Security teams should stop treating agent oversight as experimental and start treating it as governed production access.
A question worth separating out:
Q: When does zero trust fail for AI-enabled data environments?
A: Zero trust fails when verification stops at login and does not continue through data use. In AI-enabled environments, identities can remain authenticated while still copying, transforming, or exposing information that should not leave the governed workflow. Continuous policy enforcement and audit linkage are what keep the model credible.
👉 Read our full editorial: GenAI security risks expose the gap in AI agent governance
