documented real-world prompt injection attacks against RAG-based enterprise tools
Attackers exploited over 90 organizations' AI tools to steal credentials and cryptocurrency in 2025.
Selah Beck
Section
LLM Security Fundamentals
6 stories in LLM Security Fundamentals.
AI risk scoring and vendor assessment platforms mapped to OWASP LLM Top 10 and NIST AI RMF
Platforms claiming framework alignment often lack the runtime controls to prove it.
Marco Quist
Overreliance on LLM Output as a Security Risk
Treating LLM errors as user failures misses the systemic design flaw.
Bianca Espinoza
Model Denial of Service in LLM Deployments
Silent cost explosions hit LLM deployments where traditional monitoring misses them.
Marco Quist
Training Data Poisoning Attack Vectors
Malicious training data is infiltrating AI systems faster than organizations can detect it.
Bianca Espinoza
Sensitive Information Disclosure via LLM Responses
Large language models leak sensitive training data and runtime context through systematic attacks.
Selah Beck