https://www.lukaswalter.dev/tags/ai-security/ Recent content in Ai-Security on lukaswalter.dev https://www.lukaswalter.dev/images/LW%20Dev%20Thumbnail.png https://www.lukaswalter.dev/images/LW%20Dev%20Thumbnail.png Hugo -- 0.150.0 en Mon, 23 Mar 2026 00:00:00 +0000 https://www.lukaswalter.dev/posts/indirect-prompt-injection/ Mon, 23 Mar 2026 00:00:00 +0000 https://www.lukaswalter.dev/posts/indirect-prompt-injection/ Indirect prompt injection is a trust-boundary failure; treat retrieved content as untrusted data, isolate it from instructions, and validate actions before execution.