Topic starter
23/06/2026 9:21 pm
TL;DR: System prompt leakage, prompt reverse-engineering, and RAG manipulation are emerging as major LLM security risks in 2025, with Gartner projecting that by 2027 half of enterprise GenAI models will be industry- or function-specific, according to Lasso Security. Guardrails alone are not enough because security has to move into externalised controls, context-aware access, and compliance-ready architecture.
Editorial analysis by NHI Mgmt Group, based on content published by Lasso Security: “LLM Security Predictions: What’s Coming Over the Horizon in 2025?”.
Key questions
Q: What breaks when system prompts contain secrets or access rules?
A: The prompt stops being harmless configuration and becomes a live control surface.
Q: Why are leaked prompts a security and compliance risk?
A: Because they can expose both sensitive content and the logic used to handle regulated data.
Q: How can security teams test for prompt injection and reverse engineering?
A: Use red-team exercises that vary inputs, inspect outputs, and look for hidden instruction disclosure, policy boundary leaks, or unexpected retrieval behaviour.
Practitioner guidance
- Externalise prompt-sensitive controls Move credentials, connection strings, internal rules, and access decisions out of system prompts and into vaults, policy services, and workflow controls.
- Red team prompt leakage paths Test whether the model can be induced to reveal hidden instructions, safety thresholds, or retrieval logic through repeated interaction and prompt variation.
- Separate retrieval from instruction handling Treat retrieval sources, prompt construction, and answer generation as distinct control points so one failure does not expose the entire decision path.
Bottom line: System prompt leakage turns hidden instructions into an attack surface, especially when prompts carry credentials, policy, or routing logic.
Explore further
View Full Forum → | NHI Foundation Course → | Our Services → | Read the full analysis →
25/06/2026 2:37 am
System prompt leakage is not a model-only problem, it is a control-plane design failure. When prompts contain rules, credentials, or routing logic, the LLM becomes a repository for governance material that should be externalised. That breaks the assumption that the model can safely hold the very controls that constrain it. Practitioners should treat prompt content as governed infrastructure, not application text.
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: Should organisations keep access control inside the LLM or outside it?
A: Outside it. Access decisions should be enforced by external policy, vault, and retrieval controls, while the model remains a consumer of governed context. That reduces the chance that a prompt leak also becomes a privilege leak.
👉 Read our full editorial: System prompt leakage is the next LLM security fault line