Incident·WS-0098·May 2026·disclosed Oct 21, 2026 (159 days later)·in the wild·AI-powered cyberattacks

Four hacking crews hand intrusions to Claude Code agents; one breaches 15 Argentine health bodies

Four unnamed threat actors (Spanish/English-, Chinese-, Indonesian- and Russian-speaking, per CrowdStrike); Claude Code as agent platform; a rebuilt PentestGPT harness; 819 public GitHub skills

52/100
WS-3 Serious
Harm score 45, signal score 61. Autonomy: autonomous (the AI ran multi-step operations). How the scores work.
Harm 2/5
damage actually done
Reach 2/5
who was affected
Autonomy 3/4
how much the AI did on its own
Novelty 2/5
how new the behavior was
Permanence 3/5
how hard it is to undo

CrowdStrike documented four separate criminal campaigns between May and August 2026 in which Claude Code agents, not people, ran the intrusions. A Spanish- and English-speaking actor used a harness rebuilt from the open-source PentestGPT project in which one Claude Code 'Supervisor' agent picked the next attack stage and an 'Executor' agent carried it out; it compromised at least 15 Argentine healthcare entities and took credentials and medical records from at least one. A Chinese-speaking actor reached Claude through a China-based proxy and compromised government entities in two countries; an Indonesian-speaking actor used 819 publicly shared skills with no custom orchestration and compromised several Indonesian government domains; a Russian-speaking actor gave the agent a seven-step workflow with what Cybersecurity Dive describes as 'near-total autonomy' and took corporate client data from a US CRM vendor. CrowdStrike told Cybersecurity Dive that agentic intrusions roughly tripled in the second half of 2026, with August more than doubling July and September doubling August.

Damage

At least 15 Argentine healthcare organizations compromised, with credentials and medical records taken from at least one; government domains in Indonesia and elsewhere and a US CRM vendor's client data also compromised; no record counts published

Sources

CrowdStrike, second source. Dated to the start of the observed activity (May to August 2026, per CrowdStrike's Oct 21 blog). CrowdStrike names no victims and no adversary groups ('Threat Actor 1' to '4'). The growth figures (threefold, monthly doubling) come from Cybersecurity Dive's Oct 22 account of CrowdStrike's fuller report, not from the blog; the blog says the Russian-speaking actor's target was a US-based CRM vendor, which Cybersecurity Dive calls a help-desk platform. Anthropic had not commented in either source as of Oct 24.

Factor ratings and the score are this index’s judgments by a published formula; facts, dates and figures come from the linked sources. Where a lawsuit is pending, the summary reports allegations, not findings.