The threat model for applications built on language models: direct and indirect prompt injection, jailbreaks, system-prompt and training-data leakage, insecure output handling, and excessive agency in tool-using agents. Real exploit patterns from 2025 — zero-click exfiltration, confused-deputy tool calls, denial-of-wallet — and the uncomfortable reason classic input validation does not save you.
Threat-Modeling
-
The OWASP LLM Top 10 and Prompt Injection -
Secure Software Development Lifecycle: Building Security Into Every Phase A practical guide to the Secure SDLC — from threat modeling and design reviews to SAST/DAST, dependency auditing, and embedding security gates into CI/CD pipelines.