AI Guardrails Aren’t Stopping Criminal Hackers
· Safety
Hackers worldwide use agentic AI to bypass model safeguards and compromise targets, according to CrowdStrike researchers.
Criminal hackers worldwide bypass AI guardrails using agentic AI to launch successful attacks.
CrowdStrike researchers analyzed four previously unreported threat groups conducting attacks between May and August using agentic AI to bypass model safeguards. The actors operated in Chinese, Spanish and English, Indonesian, and Russian, with varying levels of sophistication but all achieving successful compromises of multiple targets.
The attackers primarily used Anthropic's Claude and open-weight Deepseek models, deliberately routing between multiple models to exploit differences in guardrails.
The threat groups circumvented safeguards by convincing models their activities were legitimate, authorized penetration testing or security evaluation. They used traditional jailbreaking techniques, added files to show approval, and in one case deployed ClawGod — a tool attempting to remove the CYBER_RISK_INSTRUCTION from Claude Code.
The most sophisticated actors built autonomous penetration testing harnesses with 'Supervisor' and 'Executor' AI agents. One group successfully compromised 15 Argentine healthcare entities stealing credentials and medical records, while another targeted government bodies in Brazil and Colombia plus private organizations across biotech, healthcare, food, retail, technology and travel sectors.
Even less technical actors succeeded using basic, publicly available tools, compromising Indonesian government domains, a Bangladeshi government domain, and private-sector targets. The pattern shows humans conducting initial probing while engaging AI for hacking at scale, demonstrating agentic AI's effectiveness for criminal operations despite existing safeguards.
Agentic AI is enabling even unsophisticated criminals to bypass model safeguards and compromise targets at scale worldwide.
Source: WIRED
More AI news
- Hugging Face’s New AI Biology Model Lets You Chat With DNA
- Microsoft says its AI tool is better than doctors at diagnosing conditions
- Anthropic takes on Muse with Claude Duet, its new AI agent
- ServiceNow and Nvidia launch Arc, a new AI agent for enterprise
- OpenAI Invests in Startup That Uses Brain Implants to Detect Cancer
`;
}
function imgFallback(el) {
if (!el.dataset.fb) { el.dataset.fb = '1'; el.removeAttribute('srcset'); el.src = el.dataset.full; }
else { el.style.visibility = 'hidden'; }
}
function formatDate(iso) {
if (!iso) return '';
return new Date(iso).toLocaleDateString('en-US', { month: 'long', day: 'numeric', year: 'numeric' });
}
function handleSubscribe(e) {
e.preventDefault();
const email = document.getElementById('inline-email').value;
e.target.reset();
goSubscribe(email, 'article');
}
// One step: the email typed on the page goes straight to Beehiiv's confirm page (no second form).
function goSubscribe(email, source) {
window.__subSource = source;
const url = 'https://magic.beehiiv.com/v1/eb0b9508-1ffd-4fb1-a63c-e762fa86569c?email=' + encodeURIComponent(email)
+ '&utm_source=aifeed.run&utm_medium=website&utm_campaign=' + encodeURIComponent(source || 'site');
// Same tab (no popup: in-app browsers like Instagram's prompt on new windows); Beehiiv sends the visitor to our thanks page after the one tap.
window.location.href = url + '&redirect_to=' + encodeURIComponent('https://aifeed.run/subscribe/thanks/'); return;
try { w.opener = null; } catch (err) {}
document.getElementById('sub-email-field').value = email;
document.getElementById('sub-form-state').style.display = 'none';
document.getElementById('sub-success-state').style.display = 'block';
document.getElementById('sub-overlay').style.display = 'flex';
document.body.style.overflow = 'hidden';
}
function openSubOverlay(email) {
document.getElementById('sub-email-field').value = email;
document.getElementById('sub-form-state').style.display = 'block';
document.getElementById('sub-success-state').style.display = 'none';
document.getElementById('sub-btn').textContent = 'Subscribe — It\'s Free →';
document.getElementById('sub-btn').disabled = false;
document.getElementById('sub-overlay').style.display = 'flex';
document.body.style.overflow = 'hidden';
}
const BEEHIIV_SUBSCRIBE_URL = 'https://magic.beehiiv.com/v1/eb0b9508-1ffd-4fb1-a63c-e762fa86569c'; // Beehiiv public Magic Link for AIFeed.run (pub_eb0b9508-…), no API key
async function submitSubscribe(e) {
e.preventDefault();
const email = document.getElementById('sub-email-field').value;
const btn = document.getElementById('sub-btn');
btn.textContent = 'Opening signup...';
btn.disabled = true;
// Opens Beehiiv's one-click confirm page for this email ("You'll be subscribed with …"). No secret client-side.
const bhUrl = BEEHIIV_SUBSCRIBE_URL + '?email=' + encodeURIComponent(email)
+ '&utm_source=aifeed.run&utm_medium=website&utm_campaign=' + encodeURIComponent(window.__subSource || 'site');
// Same tab (no popup: in-app browsers like Instagram's prompt on new windows); Beehiiv sends the visitor to our thanks page after the one tap.
window.location.href = bhUrl + '&redirect_to=' + encodeURIComponent('https://aifeed.run/subscribe/thanks/'); return;
try { w.opener = null; } catch (err) {}
document.getElementById('sub-form-state').style.display = 'none';
document.getElementById('sub-success-state').style.display = 'block';
}
function closeSubOverlay(e) {
if (e && e.target && e.target.id !== 'sub-overlay' && e.target.id !== 'sub-close-btn') return;
document.getElementById('sub-overlay').style.display = 'none';
document.body.style.overflow = '';
}
function copyLink() {
navigator.clipboard.writeText(window.location.href).then(() => {
const t = document.getElementById('toast');
t.textContent = '🔗 Link copied!';
t.classList.add('show');
setTimeout(() => t.classList.remove('show'), 2500);
});
}
function showToast() {
const t = document.getElementById('toast');
t.textContent = '🎉 You\'re subscribed! Welcome to the feed.';
t.classList.add('show');
setTimeout(() => t.classList.remove('show'), 3500);
}
function getDemoPosts() {
return [
{
id: 'demo-1', slug: 'apple-building-ai-glasses-beat-meta',
headline: 'Apple Is Building AI Glasses To Beat Meta',
summary: 'No screen. Just AI, cameras, and Siri. 4 designs. Premium acetate. Ships 2027.',
body: '