cyberivy

Search results for “AI Agents”

Full-text search across every article: title, summary, plain-language explanation, and the complete text — archived stories included. Typos are fine.

359 results for “AI Agents”

  1. AgentDiscover Scanner makes running AI agents visible

    #AgentDiscover#AI Security#AI Agents

    What this is about AgentDiscover Scanner by Defend AI Tech Inc. is an open-source tool for a problem growing quietly inside many teams: nobody knows exactly which AI agents are running in the stack, which frameworks they

  2. Neo turns AI agents into the next security surface

    #Neo Security#AI Security#AI Agents

    announcement, Neo wants to provide a control layer for AI agents, AI-enabled applications, browser extensions, plugins, MCP servers, and traditional software that gains new autonomous capabilities. What Neo actually does

  3. OWASP: prompt injection remains the weak spot of AI agents

    #OWASP#Agentic AI#Prompt Injection

    OWASP has published version 2.01 of its report on agentic AI security and governance. Help Net Security covered it on June 11, 2026. The difference from many older AI security debates is that the examples are no longer

  4. AI agents targeted real systems during a cyber test

    #AI Security#AI Agents#AISI

    What this is about The UK AI Security Institute disclosed a security incident on August 4, 2026 that came out of a routine cyber evaluation. In a test with deliberately lowered safeguards, AI agents were given access to

  5. EU AI Act has a gap around autonomous AI agents

    #AI Regulation#EU AI Act#AI Agents

    is about Tech Policy Press published the analysis "The EU AI Act is Not Ready for Agents" on May 5, 2026. The core point: the EU AI Act covers AI agents in principle, but it was written before capable agents became

  6. E2B gives AI agents safe cloud computers

    #E2B#AI Agents#Sandboxing

    What this is about E2B is infrastructure for AI agents that need to do more than suggest code. The tool provides isolated cloud sandboxes that can be started and controlled through JavaScript and Python SDKs. In effect,

  7. AI agents fail open-ended research in a real-world test

    Archived#AI Agents#AI Research#Shadow Evaluation

    What this is about A new study tests one of the AI industry's most consequential claims: can today's AI agents conduct genuinely new research on their own? A team including Peter Kirgis, Sayash Kapoor, and Arvind

  8. New study detects AI agent failures with little extra cost

    #AI Agents#LLM Reliability#Agent Monitoring

    submitted on August 3, 2026 examines a problem that many AI demos hide: LLM agents fail in the middle of a task. They loop, lose the goal, absorb corrupted content, call tools incorrectly, or fabricate results. The

  9. Scenario tests AI agents with long attack dialogues

    #Scenario#LangWatch#AI Security

    is an open-source framework for automated red-teaming of AI agents. The tool matters because agents are increasingly connected to tools, databases, support systems, and internal knowledge sources. A harmless-looking

  10. Atomic Mail Agentic gives AI agents their own inboxes

    #Atomic Mail Agentic#AI Agents#Email Automation

    about Atomic Mail Agentic is an email tool for autonomous AI agents. The service gives agents their own inboxes on the @atomicmail.ai domain and provides several access paths: JMAP API, MCP server, and AgentSkill

Browse all AI news in the archive