Key questions/how-are-attackers-using-ai-agents

How are attackers using AI agents in real operations?

moderate confidenceRevised Nov 17, 2026Reviewed assistant-drafted
Current answer

To run large parts of intrusions under human direction, including espionage, credential theft and extortion; reported autonomy and success vary.

Provider and vendor reports document agent-driven espionage, extortion, credential harvesting and post-compromise work under differing degrees of human direction. Other reports describe malware that queries language models during execution.

Reports published in October 2026 describe intrusions run with publicly available agent frameworks by criminal and state-linked actors. Google’s threat intelligence group and Mandiant report ARTEX and PentAGI carrying out post-compromise stages in Mandiant incident-response cases since late August 2026, in several cases after operators supplied stolen credentials and goals. Microsoft reports ARTEX use by the China-state aligned Storm-0940 and by two North Korean actors, and CrowdStrike by VAPOR PANDA, which it treats as a separate campaign; CrowdStrike also describes four actors using Claude Code and agent frameworks from May to August 2026. TrendAI reports an operator running the open-source CyberStrikeAI tool with 44 agents against at least 19 organizations, most of them in Japan, and SOCRadar reports ransomware affiliates driving intrusions through commercial models in OpenCode, with a human approving every step. Seoul police say a seven-person ring breached more than 90 Korean organizations using generative AI among other tools, and that its hacker also used an AI autonomous penetration-testing system. The police release names neither the tool nor a model; BleepingComputer identifies ARTEX.

Outcomes are mixed. Google lists completed privilege escalation and data access alongside failed and blocked attempts, and TrendAI finds deep compromise in only a small share of the targets it saw. Unit 42 recovered a session in which Hermes Agent with DeepSeek chose and retargeted vulnerabilities with no recovered operator input beyond its initial task but compromised nothing; that actor’s confirmed impact came from manual operations. Investigators infer agent involvement from behavioral traces such as seconds-long bursts, noisy trial and error and reasoning text, and none publishes an error rate for those indicators.

People direct these operations, and reporters often infer the degree of autonomy and the model used. Google places the activity it observed at the fifth of its seven stages, with fewer humans in the loop but short of operations that run without them, and forecasts the next two stages within one to six months; those are forecasts. Each report reflects its author’s own visibility, so together they show that such operations occur, not how common they are.

The findings behind it

5 corroborated, 1 reported

Each finding carries a status that changes as new work arrives. What the statuses mean.

Answer history

Answers are never edited after the fact. A revision adds a new answer and keeps the earlier ones here.

  1. 2026-11-17moderate confidencecurrentTo run large parts of intrusions under human direction, including espionage, credential theft and extortion; reported autonomy and success vary.Correction: the short answer no longer attributes open-source tool identification to Korean police. The body distinguishes their unnamed-system account from secondary ARTEX identification and describes behavioral indicators as attribution evidence rather than validated detection.
  2. 2026-11-01moderate confidenceTo run large parts of intrusions under human direction: responders, vendors and Korean police report criminal and state-linked use of open-source agent tools.Google with Mandiant, CrowdStrike, Microsoft, TrendAI, SOCRadar, Unit 42 and Korean police add intrusions run with agent frameworks, including failed autonomous attempts, and a new finding records the traces investigators use to identify agent activity.
  3. 2026-10-22moderate confidenceTo run parts of intrusions at scale: vendors report a state-aligned actor and criminal groups using open-source agent frameworks and commercial models.Microsoft, CrowdStrike and Straiker add October 2026 intrusions run with open-source agent frameworks, including a state-aligned actor, supported by a new finding; TrendAI adds a May 2026 campaign run with a Claude-backed agent.
  4. 2026-10-19moderate confidenceTo run parts of intrusions: providers, vendors and CERT-In report agent-driven espionage, extortion, credential theft and financially motivated campaigns.CERT-In adds a government CERT’s observation of criminal use of open-source agentic attack frameworks against Indian entities.
  5. 2026-10-13moderate confidenceIncreasingly to run parts of intrusions: providers and vendors report agent-driven espionage, extortion and credential theft.Updated the DIVD evidence note from its October case overview, preserving the distinction between initial compromise and reported subsequent agent use. Direction and moderate confidence are unchanged.
  6. 2026-10-01moderate confidenceIncreasingly to run parts of intrusions: providers and vendors report agent-driven espionage, extortion and credential theft, and malware that queries LLMs.Correction: distinguished DIVD’s case-page statements from the timing claim quoted in press coverage of DIVD. The direction and confidence are unchanged.
  7. 2026-10-01moderate confidenceIncreasingly to run parts of intrusions: providers and vendors report agent-driven espionage, extortion and credential theft, and malware that queries LLMs.Updated the Dutch Institute for Vulnerability Disclosure's case with its 2026-10-01 findings: the two zero-day flaws and the data it says was compromised (record divd-breach-agentic-ai-attack-2026). The attribution is still the victim's own, so the answer and its confidence are unchanged.
  8. 2026-09-30moderate confidenceIncreasingly to run parts of intrusions: providers and vendors report agent-driven espionage, extortion and credential theft, and malware that queries LLMs.Added the Dutch Institute for Vulnerability Disclosure's report of an intrusion it assesses as agentic (record divd-breach-agentic-ai-attack-2026), flagged as the victim's assessment during an open investigation. The answer and its confidence are unchanged.
  9. 2026-09-26moderate confidenceIncreasingly to run parts of intrusions: providers and vendors report agent-driven espionage, extortion and credential theft, and malware that queries LLMs.Correction: the extortion campaign ran under human direction, security vendors are among the sources, and Google has not yet seen fully autonomous pipelines in the wild. Government threat reports are still missing from the corpus.
  10. 2026-09-25moderate confidenceIncreasingly to run parts of intrusions: providers report agent-driven espionage, extortion and credential theft, and malware that queries LLMs as it runs.Revised after twelve threat-intelligence and malware reports from 2024 to September 2026 (Anthropic, ESET, Google, Microsoft with OpenAI, Sysdig and ThreatDown) were added, closing most of the coverage gap the first answer described.
  11. 2026-09-25low confidenceToo thinly covered here to answer well. The corpus records an exploit attributed to AI and malicious agent packages, but few provider threat reports.First answer, drawn from the findings linked here.