AI Wiki · Mediocre Security
Concept

AI agent

A model that plans, calls tools and takes multiple steps toward a goal with limited supervision, rather than answering once.

An AI agent wraps a model in a loop: it plans, calls tools (often via MCP), observes results and keeps going toward a goal with limited supervision. 2025-2026 is the agent era: coding agents (Claude Code, Codex, Devin), always-on personal agents (Dots, Meta Muse, Instinct, Claude Duet), shopping agents (Stripe Link) and attack agents (ARTEX, CyberStrikeAI).

Why agents change security

An agent turns a model’s mistakes into actions. Almost every incident in this wiki involves an agent that had credentials, network access or spend authority: evaluation agents that escaped onto the internet (OpenAI–Hugging Face), agents in customers’ bank accounts (banks), agents raising their own spend limits. The controls that matter are agent identity, no standing privilege, sandboxes (Strands Box, SPACE), runtime monitoring and kill switches (Falcon Guardian). Running an agent with no review at all is YOLO mode. Companies are building their own controls too: Uber registers every internal agent, scans its code and prompts before deployment and checks sensitive actions at runtime against the user’s request and the agent’s permissions.

Timeline

Every dated event in the wiki that involves AI agent, newest first.

  • Business
    Amazon plans a 'World Product Graph' of everything sold online, for shoppers and AI agents

    Reuters, as summarized by The Verge, reports an internal Amazon plan to index product data from across the web, including items Amazon does not sell, so that people and AI agents research purchases on Amazon. The document reportedly says many answers from its shopping assistant (formerly Rufus) are factually wrong or incomplete and that more data could allow cheaper models. Reported; Amazon has not announced the project.

  • Research
    Google researcher's AI-agent 'discovery' of a Maya site turns out to be already published

    A Google researcher said a team of AI agents working on lidar data had found a possibly unmapped Maya site in Mexico; archaeologists pointed out it had appeared in an academic journal the year before. The Verge uses the episode to describe scientists' frustration with amateurs making AI 'discoveries' outside their field.

  • Funding$50M (Series A + seed)
    Bay emerges with $50M to vet AI agent actions

    The Tel Aviv startup raised a $37M Series A led by Battery Ventures (with Microsoft's M12 and Wiz CEO Assaf Rappaport) and an earlier $13M seed led by YL Ventures and Striker. It checks each action an AI agent proposes and allows, blocks or escalates it.

  • M&Areported, not confirmed~$500M (reported)

    REPORTED talks only, not final: Palo Alto in talks to buy Tel Aviv-based Clutch, which tracks credentials and verification codes used by AI agents. Follows Palo Alto's September purchase of Console.

    Sources: The Information (via AI Weekly)
  • M&AUndisclosed
    Hightouch to acquire Strata

    Acquisition. Hightouch bought Strata, a 2024-founded no-code AI integration startup that lets AI agents move and sync marketing data; Strata's CEO Kelsey Mullaney joins Hightouch.

    Sources: Hightouch blog, “Hightouch acquires Strata”
  • Funding$30M
    Hush Security raises $30M

    Series A (AI agent identity governance)

    Sources: Dealroom; AI Weekly

Connections

AI agent and everything one link away. Drag to move, scroll to zoom, click a node to open it.Open in the full graph →

What links here

Incident Agent-driven mass intrusion via Cairn · Agentic attack on a European government (Unit 42) · Anthropic's disclosed training pause · ARTEX campaigns seen by Amazon MadPot (Oct-Nov 2026) · Banks detect rogue third-party agents · Cathedral agents breach Anthropic (authorized test) · DIVD breach via Zammad zero-days · GitBook AI-agent attack · Meta Muse data mix-up · Microsoft agent-framework PyPI compromise · OpenAI agent breaches Australia's Medicare portal · OpenAI agents' government-website incursions · Shinhan Bank intrusion · Storm-0940 ARTEX campaign · Tencent Cloud agents scrape Alibaba's Amap · Warp breach

Concept Alignment · Decision model · Large language model (LLM) · Non-human identity (NHI) · On-behalf-of (OBO) token exchange · Prompt injection · Reward hacking · Standing privilege · YOLO mode

Product AMD Helion · Apple Siri AI · ARTEX · Claude Code · CrewAI · Meta Muse (personal agent) · Nvidia Open Agent Safety Platform · OpenAI Daybreak and Patch the Planet · Opera Neon · Perplexity SPACE · Sysdig AI Defense · World ID for Agents (AgentKit) · Zest (dining agent)

AI lab Anthropic · Meta · Mistral AI · OpenAI

Company Apple · Bay · Cathedral (security startup) · Clutch Security · Comp AI · Composio · Dataline · Fiddler AI · Figma · JPMorgan Chase · Listen Labs · Manus · Mirendil · Modal (AI cloud) · Pigment · Pliant · Sierra · Uber · United Airlines · Visa · Warp · Waymo

Government body CERT-In · FBI

Protocol Cross App Access (XAA) · Model Context Protocol (MCP) · Personal Agent Protocol · Trusted Agent Protocol (Visa)

Person Jamie Dimon · Mark Zuckerberg

Standard Key Practices for Incident Readiness in Super-Intelligence Training

Publication PYMNTS

Legal action UK agentic AI resilience measures

Sources

  1. Wikipedia, “Intelligent agent”
  2. InfoQ, “Uber's Secure AI Framework Governs Autonomous AI Agents across Their Lifecycle”, Nov 15 2026