https://promptexploit.com/ Breaking and defending LLMs. Notes on prompt injection, jailbreak research, and agent security. en-us Thu, 04 Jun 2026 00:00:00 GMT https://promptexploit.com/posts/llm04-2025-data-and-model-poisoning-simple-explanation/ https://promptexploit.com/posts/llm04-2025-data-and-model-poisoning-simple-explanation/ Thu, 04 Jun 2026 00:00:00 GMT A simple explanation of OWASP LLM04 data and model poisoning. https://promptexploit.com/posts/llm03-2025-supply-chain-simple-explanation/ https://promptexploit.com/posts/llm03-2025-supply-chain-simple-explanation/ Thu, 04 Jun 2026 00:00:00 GMT A simple explanation of OWASP LLM03 supply chain risk. https://promptexploit.com/posts/llm02-2025-sensitive-information-disclosure-simple-explanation/ https://promptexploit.com/posts/llm02-2025-sensitive-information-disclosure-simple-explanation/ Thu, 04 Jun 2026 00:00:00 GMT A simple explanation of OWASP LLM02 sensitive information disclosure. https://promptexploit.com/posts/llm01-2025-prompt-injection-simple-explanation/ https://promptexploit.com/posts/llm01-2025-prompt-injection-simple-explanation/ Thu, 04 Jun 2026 00:00:00 GMT A simple explanation of OWASP LLM01 prompt injection. https://promptexploit.com/posts/owasp-genai-llm-top-10-simple-explanation/ https://promptexploit.com/posts/owasp-genai-llm-top-10-simple-explanation/ Fri, 29 May 2026 00:00:00 GMT A plain-language explanation of the OWASP GenAI Security Project and the 2025 LLM Top 10. https://promptexploit.com/posts/indirect-prompt-injection-101/ https://promptexploit.com/posts/indirect-prompt-injection-101/ Fri, 15 May 2026 00:00:00 GMT How untrusted content smuggles instructions into a model. https://promptexploit.com/posts/isolating-tool-output-in-agents/ https://promptexploit.com/posts/isolating-tool-output-in-agents/ Mon, 20 Apr 2026 00:00:00 GMT Patterns that stop agents from trusting their inputs blindly. https://promptexploit.com/posts/building-a-jailbreak-eval-harness/ https://promptexploit.com/posts/building-a-jailbreak-eval-harness/ Tue, 10 Mar 2026 00:00:00 GMT Measuring model robustness with a repeatable test suite.