EN
Sign inGet started
Glossary

Prompt leaking

What is Prompt leaking?

Prompt leaking refers to the unintended disclosure of an AI system's internal instructions, for instance when a chatbot reveals its system prompt in response to a cleverly worded request. This becomes a problem if those instructions contain business logic, internal information or even credentials. The OWASP list for LLM applications names this risk explicitly. The most effective safeguard is to write instructions as if they could become public, never store secrets in them and check outputs as well.

How KI.ordo helps

The KI.ordo template “Chatbot security audit” helps check agent instructions for this risk; passwords and other secrets should never be placed in them.

Learn more →: Prompt leaking

Matching templates

Topics

  • AI security
  • system prompt
  • data protection

Try KI.ordo

Agents, flows and templates in one workspace – free 24-hour demo.

Start demo
← All terms

Related terms

System Prompt Extraction

System prompt extraction describes attempts to make a chatbot or AI agent reveal its hidden system instructions. If such an attempt succeeds, the result is called prompt leaking: extraction is the attack, the leak is the consequence. Effective protection starts with keeping passwords, keys and confidential rules out of instructions and assuming they may become public; input checks and regular testing add further safeguards.

  • Security
  • Prompt leaking
  • +1
Template

AI Firewall

An AI firewall is a protective layer between users, data sources and an AI model. It screens inputs for manipulation attempts such as prompt injection or jailbreaks and checks outputs, for example for confidential data or unwanted content, before passing them on. It may use rules, classification models or a second language model. An AI firewall reduces risk but does not offer complete protection and replaces neither limited permissions nor testing.

  • Security
  • Prompt injection
  • +1
Template

OWASP LLM Top 10

The OWASP Top 10 for LLM Applications is a list of the most important security risks in applications built on large language models, published by the OWASP GenAI Security Project. The current 2026 edition appeared in August 2026 (as of October 2026) and covers: prompt injection, sensitive information disclosure, excessive agency, supply chain, data and model poisoning, unbounded consumption, misinformation, hidden context exposure, vector and embedding weaknesses, and improper output handling. It serves as a checklist for development and audits.

  • security
  • standard
  • +1
Template

Chatbot security audit

A chatbot security audit is a structured review of whether an AI chatbot adequately protects confidential data, its internal instructions and its permissions to act. It examines, among other things, susceptibility to prompt injection, unintended disclosure of information and overly broad access to tools – often following the OWASP Top 10 for LLM Applications. The result is a report with a rating per risk area and concrete measures.

  • security
  • audit
  • +1
Template