Notifications
Clear all
Topic starter
21/08/2026 4:50 pm
TL;DR: LLM security in 2025 is shifting from prompt injection toward data exposure, identity misuse, and over-privileged AI systems, according to Sentra. The operational lesson is that RAG, fine-tuning, and tool-calling expand the attack surface faster than point-in-time reviews can keep up.
NHIMG editorial — based on content published by Sentra: LLM security in 2025 and the risks of training data exposure
By the numbers:
- 80% of organisations report their AI agents have already performed actions beyond their intended scope, including accessing unauthorised systems, sharing sensitive data, and revealing access credentials.
- When AWS credentials are exposed publicly, attackers attempt access within an average of 17 minutes.
Questions worth separating out
Q: How should security teams govern AI models that can call tools and access data?
A: Security teams should govern AI models as non-human identities with named owners, limited scope, short-lived credentials, and continuous authorization.
Q: Why do conversational AI systems create new identity and access risks?
A: Because they can combine data retrieval, decision-making, and execution in a single interaction.
Q: What do organisations get wrong about securing LLMs connected to tools?
A: Many teams focus on content moderation and miss the execution layer.
Practitioner guidance
- Tighten retrieval-source governance Inventory every RAG source, classify the data it can expose, and require explicit approval for any dataset that feeds inference time access.
- Constrain AI tool permissions Assign task-scoped permissions to every agent or model-connected tool, then remove broad cloud and SaaS entitlements that are not required for the workflow.
- Classify and sanitize training inputs Run data discovery and sanitization before any fine-tuning or continual training step, with special handling for PII, secrets, and regulated records.
What's in the full article
Sentra's full article covers the operational detail this post intentionally leaves for the source:
- How Sentra applies DSPM, DAG, and DDR together across LLM training data workflows
- The specific data discovery and classification approach used to detect sensitive content in unstructured sources
- How the platform flags suspicious user, app, and machine identity activity tied to AI pipelines
- Why the article positions cloud-native data security as the control layer for AI training and inference
👉 Read Sentra's analysis of LLM security risks in 2025 →
LLM training data exposure and access control gaps in 2025?
Explore further
21/08/2026 5:08 pm
AI security has become an identity governance problem, not just a model safety problem. The article correctly places data exposure and excessive agency at the centre of LLM risk, but the deeper issue is who and what is authorised to move data, call tools, and inherit privilege. Once an LLM is connected to internal systems, its security posture depends on IAM, PAM, and NHI controls as much as on the model itself. Practitioners should treat model workflows as governed access chains, not isolated AI features.
A question worth separating out:
Q: How can security teams tell whether AI agent access is drifting out of scope?
A: Look for agents touching systems, data sets, or tools that are outside the intended task boundary, especially when those actions are not part of the approved workflow. Behavioural baselines, entitlement logs, and cross-system correlation are the key signals. If the agent can act meaningfully outside its original purpose, scope drift is already happening.
👉 Read our full editorial: LLM security in 2025 is now a data and identity problem
