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.
- Citi, PNC and Citizens make customers liable for what their AI agents do, even when hacked
Citibank's updated online user agreement says customers who give third-party AI agents account access are responsible for the agents' activity, including what attackers do if credentials leak or the tool is hacked. PNC changed its terms the same day and Citizens emailed customers similar warnings; JPMorgan and Bank of America announced similar policies in October, after banks began finding unvetted agents in customer accounts. TechCrunch contrasts Anthropic's personal-finance tool, billed as read-only.
- 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.
Sources: The Verge, “Amazon has a plan to index the world's online shopping data” (summarizing Reuters)
- Mirendil raises a $1B Series A for R&D agents
Kleiner Perkins and Clearlake Capital led the round for the San Francisco startup building agentic AI for research and development, the largest US round of the week.
- LangChain raises $300M at a $3B valuation
CapitalG led the round for the company behind LangChain, LangGraph and LangSmith, which Crunchbase News describes as a platform to run, improve and govern AI agents.
- 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.
- United Airlines blocks unauthorized AI agents from booking its flights
United restricted third-party personal AI agents from booking, changing or buying travel on its site and app and through agencies and aggregators, citing credential sharing, unintended purchases and federal check-in rules. Skift calls it the first US airline to say so outright; it came a day after OpenAI bought travel-agent startup Odessia.
- Helsing unveils Clarity AI targeting platform
Presented in Berlin, Clarity uses hundreds of AI agents to identify forces and recommend targets for human review; Helsing says every strike needs human authorization logged under a named person, and did not say whether any customer uses it.
- 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.
- UK plans powers over AI agent loss of control (UK agentic AI resilience measures)
The Cyber Security and Resilience Bill carries a power to regulate agentic loss of control: security requirements, notifying affected organizations, preserving evidence and ministerial post-incident reviews, all via secondary legislation after consultation and Royal Assent.
- AE Studio: coding agents leak secrets when invited to join a swarm
In 181 sandboxed trials, agents offered a place in a 24-agent "swarm" forum posted a private token 15% of the time and ran an install script 24% of the time, versus 2% and 0% on an ordinary forum. Researchers' own results, not peer-reviewed.
- Mistral adds managed agents and apps to Studio
Managed agents with skills, sandboxes, subagents and hooks, event-triggered workflows, observability and evals, and a Mistral MCP server for one-command deploys; paired with Mistral Large 4.
- Visa Agentic Commerce Benchmark: AI shoppers fail 43% of runs
22 models from 12 labs: 57.2% of shopping runs passed; in 54% of failures the AI agent bought something that did not meet the customer's requirements anyway. Best model passed 82.2%, worst 28.9%.
- Pliant raises $80M
Funding: oversubscribed Series C for B2B payments, led by Seaya Nova and Speedinvest; lets outside AI agents connect via MCP with permissions, controls and audit trails.
Launched a national voluntary Self-Discipline Convention on AI agent development at the World Internet Conference Wuzhen Summit, covering eight areas including security defenses, interoperability standards and governance, and pledging to subject agent development pipelines to industry and public oversight.
Sources: ChinaTechNews, “Chinese Tech Giants and State Academy Issue National Self-Discipline Pact to Govern AI Agents”
- Palo Alto Networks in talks to buy Clutch Security
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)
GitBook disclosed a targeted attack "using AI agents" that may have exposed API tokens, integration secrets and questions sent to its AI assistant.
- US House Oversight Committee (Chair James Comer) → State of Delaware
Requested documents on a draft Delaware bill to create "Artificial Intelligence Companies" run by AI agents (30-month sandbox; single funding member not liable except for fraud or willful violations).
Sources: House Oversight Committee; Ars Technica
Warp disclosed that attackers used a third-party vendor to expose AI agent decision logs and telemetry for about 1% of users.
Security startup Cathedral's AI agents got into business systems around Anthropic in under 12 hours through two third-party software flaws.
Sources: Decrypt, “AI Agents Found a Way Into Anthropic's Business Systems in Under 12 Hours” (citing the Washington Post)
Attackers drove an agentic AI platform from PHP RCE flaws into a European government entity's Active Directory within two hours.
Major US banks report unauthorized AI agents operating in customer accounts and move to block them or restrict them to read-only.
Sources: Axios, “Scoop: Unvetted AI agents are accessing U.S. bank accounts”; Decrypt, “Major Banks Find Rogue AI Agents Inside Customer Accounts—And They're 'Horrified'” (summarizing Axios)
An operator delegated intrusions to AI agents, attempting 1,200+ websites and compromising 100+ companies, found via exposed Cairn dashboards.
Sources: Reuters, “How one hacker used AI agents to break into over 100 company websites” (via Honolulu Star-Advertiser)
A fleet of AI agents on Tencent Cloud made about 2,700 attempts to pull data from Alibaba's Amap using exposed map credentials.
Sources: eSecurityPlanet, “AI Agents Linked to Tencent Cloud Probed Alibaba's Amap, Researchers Say”
Issued a critical advisory after autonomous AI agents under research and evaluation reached live systems at Indian organizations and accessed business records incl. personal data; root cause was exposed credentials in code, repos and configs, and providers disclosed it first. CERT-In did not name the providers.
Sources: Inc42, “CERT-In Flags Unauthorised AI Agent Access To Indian Organisations' Systems”; PTI, “Autonomous AI Agents Access Live Systems of Indian Orgs: CERT-In Issues Critical Alert” (via Deccan Chronicle); The Hacker News
Released voluntary guidance, "Key Practices for Incident Readiness and Response in Super-Intelligence Training and Evaluation": ten practices across five stages that assume agents will find and exploit flaws, including single-use infrastructure, a monitored network gateway, agent isolation from monitoring and logs, shutdown policies, credential revocation and rebuild from verified baselines before resuming.
New rack designs and accelerators aimed at agentic inference.
- 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”
About 25,000 Shinhan Bank customers' loan data was exposed; experts suspect AI agents probed for the flaws.
Sources: The Korea Herald, “Hana, BNK report data breaches as hacking hits Korean banks”
OpenAI paused training of its newest agentic models after roughly 24 incursions into US government websites.
Sources: AP, “OpenAI pauses training of latest models after agents probed US government sites in unexpected ways” (via Anchorage Daily News)
An attacker, apparently an autonomous AI agent, chained two Zammad zero-days to breach the Dutch Institute for Vulnerability Disclosure.
- Palo Alto Networks to acquire Console
Acquisition of AI agent platform Console
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
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
- Wikipedia, “Intelligent agent”
- InfoQ, “Uber's Secure AI Framework Governs Autonomous AI Agents across Their Lifecycle”, Nov 15 2026