notebook / tag

#agent-security

2 entries with this tag.

Jul 22, 2026 / 10 min / cybersecurity

The Agentic Attack Surface Does Not Stay Still

Four recent papers show why LLM security now has to cover memory, retrieval, tools, identity, delegation, interfaces, and the infrastructure around the model.

#aisecops #agent-security #threat-modeling #research

Jul 18, 2026 / 6 min / cybersecurity

Using OWASP's Agentic Top 10 to Govern Systems That Act

The OWASP Agentic Top 10 moves security beyond model output and into goals, tools, identities, memory, delegation, and runtime control.

#aisecops #frameworks #owasp #agent-security