Notifications
Clear all
Topic starter
06/06/2026 11:16 am
TL;DR: Enterprise AI is creating six active security threat vectors, including prompt injection, data exfiltration, supply chain compromise, shadow AI, agent misuse, and AI-powered social engineering, while legacy DLP, browser monitoring, and human-centric IAM struggle to see conversational context or intent, according to WitnessAI. The governance shift is from monitoring static workflows to controlling runtime behaviour across AI, agents, and human users.
NHIMG editorial — based on content published by WitnessAI: enterprise AI security threats and the controls needed to govern them
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%).
- 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 call APIs and query databases?
A: Security teams should govern AI agents as runtime actors, not passive applications.
Q: Why do legacy IAM and DLP controls fail for enterprise AI workflows?
A: Legacy IAM and DLP fail because they were built for predictable users, static data patterns, and observable workflows.
Q: What do organisations get wrong about shadow AI risk?
A: The common mistake is treating shadow AI as a policy exception instead of a discoverability problem.
Practitioner guidance
- Discover unmanaged AI use across the enterprise Inventory copilots, browser assistants, plugins, IDE integrations, and agent connections before trying to write policy.
- Replace keyword-only DLP with intent-aware policy checks Classify prompts and outputs by task intent, sensitivity, and expected business purpose.
- Bind agent tool use to explicit runtime guardrails Require pre-execution checkpoints for external API calls, database queries, and high-impact workflow steps.
What's in the full article
WitnessAI's full article covers the operational detail this post intentionally leaves for the source:
- How the vendor models six AI threat vectors across prompt injection, shadow AI, and agent misuse.
- The specific mechanics behind its Observe, Control, and Protect operating model for enterprise AI.
- How its bidirectional runtime guardrails are positioned to handle pre-execution and response-time policy decisions.
- The product-facing description of Witness Attack and the implementation detail behind its red-team testing workflow.
👉 Read WitnessAI's analysis of enterprise AI security threats and runtime controls →
Enterprise AI attack surface: what IAM teams need to know?
Explore further
06/06/2026 11:58 am
Legacy IAM was designed for predictable human workflows, not for systems that interpret context and act on it. Human-centric identity controls assume a user requests access, a system evaluates the request, and an operator can still intervene before high-risk action occurs. That assumption fails when an AI system can infer intent, invoke tools, and complete work inside a single interaction. The implication is not simply that more policy is needed, but that the governance model itself no longer matches the actor.
A few things that frame the scale:
- 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%), according to AI Agents: The New Attack Surface report.
- Only 52% of companies can track and audit the data their AI agents access, leaving 48% with a complete blind spot for compliance and breach investigation.
A question worth separating out:
Q: Should organisations treat autonomous agents like human users or service accounts?
A: Organisations should not treat autonomous agents as simple human analogues. They behave like governed non-human identities with added runtime decision-making, so they need identity boundaries, action checkpoints, and clear accountability. Human-style certification cycles alone are too slow for systems that can complete sensitive work within one session.
👉 Read our full editorial: Enterprise AI security threats expose gaps in legacy IAM controls
