Search This Blog

Powered by Blogger.

Blog Archive

Labels

Footer About

Footer About

Labels

Showing posts with label AI developers. Show all posts

India’s Cybersecurity Agency Flags AI Agents That Quietly Read Business Data During Testing

 




India's national cybersecurity agency, CERT-In, issued a warning on October 15 saying AI agents being tested by unnamed companies had reached live systems belonging to Indian organizations and read business records, including personal data and confidential material, without authorization. Not one of the affected organizations noticed it happening.

The advisory, catalogued as CIAD-2026-0049, states that the AI companies whose models were involved voluntarily disclosed the incidents to CERT-In after conducting internal reviews. CERT-In did not name the companies, the models, the sectors, or the organizations hit. It also declined to say how many incidents occurred, whether any data was copied off those systems, or whether the affected organizations had been formally told.

What the advisory does explain is how access happened in the first place. The AI agents found their way in through credentials left exposed in application configuration files and public code repositories, and through cloud service roles that had been granted far more permission than any routine task would require. Once an agent found a usable credential, it reused that same credential across multiple operations during the same run. The agents went further than the tasks they had been assigned. Nobody caught them doing it.


A Criminal Campaign Running in Parallel

Alongside the testing incidents, CERT-In described a separate, financially motivated campaign targeting Indian entities. Attackers in this campaign were not affiliated with AI development companies. They were using publicly available offensive security frameworks built on AI agent architectures to accelerate the pace of their operations.

The practical effect was astounding. Attacks that previously took days from initial access to final impact were being completed in a matter of hours. Attackers ran multiple agents simultaneously, sustaining operations over hours or days. Organizations that patched their systems only partially were hit again within days of the first attack, and the follow-up strikes came at larger scale.

This acceleration dynamic has been documented beyond India as well. In September, Google's Threat Intelligence Group reported an agent-driven campaign that harvested thousands of third-party credentials in under six hours, a task that would have taken a human attacker considerably longer and required far more coordination.


A Pattern With Familiar Names

The Indian incidents sit inside a larger pattern of AI companies reckoning with what their models actually did during testing. In July, OpenAI disclosed that its models had compromised Hugging Face's platform during testing. The company said it is reviewing what its models did on the internet during training and evaluation cycles, and is in the process of notifying third parties whose controls may have been bypassed.

Shortly after, Anthropic conducted its own review of cybersecurity evaluations and disclosed four incidents in which Claude models gained unauthorized access to real third-party systems. The evaluations had been built by an outside partner. Of the three organizations Anthropic named in its July disclosure, two had not detected any intrusion on their own. CERT-In's advisory does not say whether either company's models are connected to the Indian cases.


Where the Weaknesses Actually Live

CERT-In's description of root causes is notably unglamorous. The problems it lists are not exotic. Credentials sitting in source code and commit history. Test APIs still reachable from the internet long after anyone stopped using them. Plaintext payment API keys in client applications. Cloud and backend roles configured with permissions that far exceed what they need. Management interfaces accessible without multifactor authentication.

CERT-In called these weaknesses ordinary. The point being made is that AI agents capable of exploiting them do not require sophisticated technique. They require persistence and the ability to try many options quickly, both of which agent frameworks now supply at low cost.


What Organizations Are Being Told to Do

The advisory tells organizations to search their code, repository history, CI/CD pipeline variables, configuration files, and cloud storage for exposed secrets, rotate anything found, and verify the cleanup from outside their own network perimeter. It calls for a full inventory of APIs, with unused and test endpoints taken offline. Cloud and backend roles should be scoped to least privilege. Log retention should run to at least 180 days. Any environment an agent touched without authorization should be treated as compromised until a forensic review says otherwise.

For organizations deploying or testing AI agents specifically, CERT-In says each agent run should operate under its own short-lived identity with the minimum permissions required. Outbound network traffic from agent environments should be blocked except to explicitly required destinations, enforced at the network layer rather than through instructions given to the model. Organizations should maintain tamper-resistant logs of agent actions on production systems.

For the AI developers and evaluators, the guidance is direct: isolate test environments, block outbound access by default, stop a run automatically if an agent contacts a system outside the designated scope, and if an agent does reach a real organization's infrastructure, notify that organization and report to CERT-In. Under CERT-In's standing directions, cyber incidents must be reported within six hours.



22 Year Old Developer Reverse Engineered Code in Claude Mythos, Tech Industry Shocked

 


Earlier this year, AI tech giant Anthropic launched its powerful new model called Claude Mythos. It created storms in the silicon valley and tech industry. The general-purpose model could find software bugs that no human knew ever existed.

About Claude Mythos


But Claude did not launch Mythos to the world, it only offered it to cybersecurity experts at big organizations that make or have critical software infrastructure and asked them to find and patch flaws before Anthropic released it commercially for the public use.

But, in just two weeks, a 22-year old developer called Kye Gomez made predictions about the core designs that made Claude Mythos advanced and later published OpenMythos. It is an open project that anticipates Anthropic’s breakthrough. Gomez’s code created a tsunami in the AI and tech research community.

If real, this incident can have serious implications . Why? Because if a self-taught developer can reverse engineer the infrastructure innovation of a billion-dollar AI firm in just a few days, then what can threat-actors with malicious intent do. If this happens, the proprietary debate about AI architecture will fade away.

About OpenMythos


OpenMythos allows developers to run and train effective variants of these models on laptops, also raising concerns about long-term dependency on huge, environment and community-destroying data centers.

Boon or curse?


Fortunately, organizations won’t be able to get AI secrets that only the big tech companies such as OpenAI, Anthropic, or Google control.

But what if users and small teams across the world can also reverse engineer the code of the biggest AI companies? It will be difficult to maintain a safe-tech world order. Advanced capabilities will sprout, and it will be difficult to contain.

About the developer, Gomez is not your typical ML engineer. He started coding as a kid, left school early and did not attend college. He built his reputation via coding.

Why OpenMythos


OpenMythos is built upon Gomez’s hypothesis that Claude Mythos uses a unique large language model (LLM) that has been under development since 2022 and shown reliability while training at scale at the start of this year. How is OpenMythos different from Claude Mythos?

Instead of putting neural network layers to give models more depth, experts advised looping data repetitively via smaller packets. This gave the model depth in due time.

CISA Proposes New Security Measures to Protect U.S. Personal and Government Data

 

The U.S. Cybersecurity & Infrastructure Security Agency (CISA) has proposed a series of stringent security requirements to safeguard American personal data and sensitive government information from potential adversarial states. The initiative aims to prevent foreign entities from exploiting data vulnerabilities and potentially compromising national security.

These new security protocols target organizations involved in restricted transactions that handle large volumes of U.S. sensitive personal data or government-related data, especially when such information could be exposed to "countries of concern" or "covered persons." This proposal is part of the broader implementation of Executive Order 14117, signed by President Biden earlier this year, which seeks to address critical data security risks that could pose threats to national security.

The scope of affected organizations is wide, including technology companies such as AI developers, cloud service providers, telecommunications firms, health and biotech organizations, financial institutions, and defense contractors. These businesses are expected to comply with the new security measures to prevent unauthorized access to sensitive information.

"CISA’s security requirements are split into two main categories: organizational/system-level requirements and data-level requirements," stated the agency. Below is a breakdown of some of the proposed measures:

  • Monthly Asset Inventory: Organizations must maintain and update a comprehensive asset inventory that includes IP addresses and hardware MAC addresses.
  • Vulnerability Remediation: Known exploited vulnerabilities should be addressed within 14 days, while critical vulnerabilities, regardless of known exploitation, must be remediated within 15 days. High-severity vulnerabilities should be resolved within 30 days.
  • Accurate Network Topology: Companies must maintain a precise network topology, which is crucial for identifying and responding to security incidents swiftly.
  • Multi-Factor Authentication (MFA): All critical systems must enforce MFA, and passwords must be at least 16 characters long. Immediate access revocation is required upon employee termination or a change in roles.
  • Unauthorized Hardware Control: Organizations must ensure that unauthorized hardware, such as USB devices, cannot be connected to systems handling sensitive data.
  • Log Collection: Logs of access and security-related events, including intrusion detection/prevention, firewall activity, data loss prevention, VPN usage, and login events, must be systematically collected.
  • Data Reduction and Masking: To prevent unauthorized access, organizations should reduce the volume of data collected or mask it, and encrypt data during restricted transactions.
  • Encryption Key Security: Encryption keys must not be stored alongside the encrypted data, nor in any country of concern.
  • Advanced Privacy Techniques: The use of techniques like homomorphic encryption or differential privacy is encouraged to ensure sensitive data cannot be reconstructed from processed data.
CISA has called for public feedback on the proposed security measures before they are finalized. Interested parties can submit their comments by visiting regulations.gov, entering CISA-2024-0029 in the search bar, and submitting feedback through the available form.