14:32
2026-09-10
research.checkpoint.com
ai-safety
PuzzleMask: Abusing Plain Prose as a Covert AI Attack Vector
A prompt-crafting technique called PuzzleMask hides policy-violating payloads in plain-English prose to slip past LLM gatekeepers, and in testing across 23 crafted prompts, four quick-check models ā gā¦