Analysis · curated 21 Jul 2026
Prompt Injection: The XSS of LLMs | Tomasus
First reported · updated · 3 reports medium.com
Coverage timeline
Why it matters
Prompt injection is ranked OWASP's highest-severity LLM risk and, as the article stresses, cannot be fully patched because it stems from how current LLM architectures process input, so defenders must design mitigations around an inherent weakness rather than expect a fix.
An educational explainer, "Prompt Injection: The XSS of LLMs," describes the architectural root cause of prompt injection: LLMs concatenate system and user prompts into a single token stream with no structural separation, so the model cannot reliably distinguish developer instructions from attacker-supplied input. It covers system vs. user prompts, multi-turn conversation context, and how multimodal inputs extend the attack surface, referencing OWASP LLM01:2025 and the foundational indirect prompt injection research.