Tag: agentic-ai

All the articles with the tag "agentic-ai".

• Lakera Agent Breaker: Thingularity — Tool Recon 101

  13 Jul, 2026

  First level of Lakera's Agent Breaker (the spiritual sequel to Gandalf) targets a full agent setup instead of a single LLM. Enumeration is still step one: get the agent to disclose its own tools, parameters, and endpoints before touching any of them.

• HTB Redeemer — Reading an Agent's Memory

  13 Mar, 2026

  HackTheBox Redeemer exploits unauthenticated Redis to enumerate and extract stored keys. In agentic AI systems, an open Redis instance doesn't just leak cached data — it exposes the agent's working memory, and with write access, lets an attacker inject false context the agent will act on.