Articles tagged #agents
2 articles
securityransomwarejadepuffer
JadePuffer: A Langflow Instance, an LLM, and a 31-Second Failure Loop
JadePuffer, the first LLM-driven ransomware attack, shows why AI orchestration platforms need kernel-level runtime enforcement, not just model guardrails.
Jul 20, 20269 min read
auditsecurityagents
What Really Happened In There? A Tamper-Evident Audit Trail for AI Agents
How nono records every AI agent action in an append-only Merkle tree with cryptographic proof the record was not forged, edited, or truncated.
Apr 22, 202615 min read