TL;DR: Prompt injection, data exposure, model poisoning, extraction and supply chain abuse show why LLM security is broader than one control layer, Panther says. Natural-language systems need governance over prompts, retrieval content, tool permissions and outputs because the risky action often happens after prompting.
Editorial analysis by NHI Mgmt Group, based on content published by Panther: “What Is LLM Security? Risks, Vulnerabilities, and Best Practices”.
By the numbers:
- 13% of organisations reported breaches involving AI models or applications in 2024.
- 97% of those organisations lacked proper AI access controls.
Key questions
Q: Why do LLMs increase data exposure risk when employees use them for everyday work?
A: LLMs increase exposure risk because users often paste sensitive business data into prompts, connectors can pull data from approved systems, and outputs can repeat confidential material.
Q: What are the signs that an LLM’s safety controls are failing in practice?
A: Common warning signs include toxic or biased responses, inconsistent refusal behavior, over-acceptance of harmful prompts, and weak handling of demographic-sensitive content.
Q: What fails when LLMs are protected only with traditional application security controls?
A: Traditional controls fail because LLMs collapse trusted and untrusted text into the same context window, so signatures, protocol checks, and ordinary DLP rules often miss prompt injection, retrieval poisoning, and model-driven abuse.
Practitioner guidance
- Enforce least-privilege tool access for LLMs Limit each model or agent to the smallest set of read and write actions it genuinely needs, and separate retrieval, execution, and administration permissions.
- Validate retrieved content before prompt injection Inspect RAG sources, knowledge base entries, and external content for malicious instructions before they enter the model context window.
- Treat model outputs as untrusted data Run every LLM response through the same validation logic you would apply to user input before sending it to a database, shell, or downstream API.
Bottom line: LLM security problems arise because natural-language systems do not preserve the same trust boundaries that conventional applications rely on.
Glossary terms: Prompt Injection (Agentic), Retrieval-augmented Generation, Model Extraction, Tool-Bearing Agent
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
LLM security is now an identity and delegation problem, not just a content-safety problem. Once a model can query tools, retrieve data, or trigger workflows, the core risk becomes who or what is allowed to act through it. That makes access governance, approval boundaries, and identity-bound permissions central to the control model. Practitioners should treat model-mediated action as a governed delegation chain, not as plain application output.
A few things that frame the scale:
- AI-related credential leaks surged 81.5% year-over-year in 2025, with the surrounding AI infrastructure leaking 5x faster than core LLM providers, according to the State of Secrets Sprawl 2026.
A question worth separating out:
Q: How should security teams govern LLMs that can call tools or run code?
A: Security teams should govern them as privileged workloads, not as chat interfaces. Every tool call needs server-side authorization, schema validation, and a dedicated identity with minimal scope. If a model can influence code execution, treat that path like a production admin channel and apply least privilege, logging, and runtime isolation.
👉 Read our full editorial: LLM security gaps show why traditional controls miss AI threats