CERT-In gets access to Anthropic’s Mythos AI to test cyber vulnerabilities

SENSEX 76,917.85

+ 1,225.07

NIFTY 23,810.85

+ 370.05

CRUDEOIL 9,080.00

+ 8.00

GOLD 139,376.00

 -810.00

SILVER 180,000.00

 -3,779.00

SENSEX 76,917.85

+ 1,225.07

NIFTY 23,810.85

+ 370.05

NIFTY 23,810.85

+ 370.05

CRUDEOIL 9,080.00

+ 8.00

CRUDEOIL 9,080.00

+ 8.00

GOLD 139,376.00

 -810.00

'; } document.getElementById("lgdv").innerHTML = htmlElements; } function numberformat(i) { return Number(parseFloat(i).toFixed(2)).toLocaleString('en', { minimumFractionDigits: 2 }) } async function gatherResponse(response) { const { headers } = response; const contentType = headers.get('content-type') || ''; if (contentType.includes('application/json')) { return await response.json() } return response.text(); } function getWidth() { if (Math.max(document.body.scrollWidth,document.documentElement.scrollWidth,document.body.offsetWidth,document.documentElement.offsetWidth,document.documentElement.clientWidth) > 991) { document.getElementById("mob").style.display = "none"; document.getElementById("lgdv").style.display = "block"; } else { document.getElementById("mob").style.display = "block"; document.getElementById("lgdv").style.display = "none"; } } getWidth(); THIS AD SUPPORTS OUR JOURNALISM. SUBSCRIBE FOR MINIMAL ADS.THIS AD SUPPORTS OUR JOURNALISM. SUBSCRIBE FOR MINIMAL ADS.

Agency to examine AI model’s ability to detect and potentially exploit security flaws in controlled environment following incidents involving unauthorised access to Indian companies’ systems

By S Ronendra Singh

Updated - November 03, 2026 at 09:45 PM. | New Delhi, November 3

The move comes in the wake of incidents last month in which autonomous AI agents gained unauthorised access to systems belonging to Indian enterprises. | Photo Credit: Reuters

In a significant development, Indian Computer Emergency Response Team (CERT-In), the Centre’s nodal agency for responding to cybersecurity incidents, has secured access to Anthropic’s advanced artificial intelligence model Claude Mythos to conduct experiments on identifying and potentially exploiting software vulnerabilities, government sources said on Tuesday.

The move comes in the wake of incidents last month in which autonomous AI agents gained unauthorised access to systems belonging to Indian enterprises.

Assessing risks

CERT-In is examining the model’s ability not only to detect security vulnerabilities but also to potentially exploit them in controlled environments, allowing the agency to assess the risks posed by increasingly capable AI systems and strengthen India’s cyber defences.

“When you look at what we are doing in cyber security, we have not been able to have access to Mythos. Now CERT-In has just got the access...but we don’t want to send out everything on the cloud and send it all over the place, we better do it in a closed door environment and we are doing it, and we are finding the efficiencies improving. Originally, we were doing it about 60 per cent of what when Mythos came in, but we are closer to about 80-85 per cent now. It is detecting issues, we are able to patch, and we are able to go forward,” a senior government official said.

The access is particularly significant given the cybersecurity concerns raised last month when autonomous AI agents, deployed by AI companies for research and evaluation exercises, accessed live systems of Indian organisations without authorisation.

The official said several organisations, particularly small and medium enterprises, could have suffered serious breaches had CERT-In not intervened to alert them to the vulnerabilities and issue advisories.

“Both in the case of Anthropic and in the case of OpenAI, they themselves found out much later that this thing (model) has escaped, then they started notifying entities across the world as to where they are. The minute it came to India, both of them realised that they all have to tell us —CERT-In — before the entities. So, they told us and simultaneously, but number of months had passed,” the official said.

Cybersecurity system

The incidents have also reinforced the need for companies to strengthen their internal cybersecurity systems and regularly audit their digital infrastructure, the official said.

“When we issued the detailed cybersecurity audit guidelines a year and a half ago, a lot of people came back to us and said this is such a long thing and why are you doing this, but now in the hindsight, I think that was relevant...number of things have been caught through that process,” the official added.

Published on November 3, 2026

THIS AD SUPPORTS OUR JOURNALISM. SUBSCRIBE FOR MINIMAL ADS. THIS AD SUPPORTS OUR JOURNALISM. SUBSCRIBE FOR MINIMAL ADS. THIS AD SUPPORTS OUR JOURNALISM. SUBSCRIBE FOR MINIMAL ADS. THIS AD SUPPORTS OUR JOURNALISM. SUBSCRIBE FOR MINIMAL ADS.Sign into Unlock benefits!

• Access 10 free stories per month
• Get notified by email for early preview to new features, discounts & offers