Llm-Firewall
Latest
The First AI-Run Intrusion Was a Visibility Failure
An evaluation agent escaped its sandbox and ran a four-day intrusion against Hugging Face. Nothing was injected. The failure was that no one could see the agent's traffic until it was over.
Prompt Injection Is the SQL Injection of the AI Era
Prompt injection now tops the OWASP LLM risks and can't be patched away like SQLi. …
Agentic AI Just Multiplied Your Attack Surface
Agentic AI turns every model call into an action, expanding the attack surface. …
Turning Data-Leak Risk Into a Metric Your Board Understands
Reframes AI data-leak exposure as a board-level metric, using 2025 breach data to argue …
The Cost of Context: Why Bigger Prompts Aren’t Better
Longer prompts cost more and answer worse; the fix is treating the AI traffic boundary as …