UNC6993
actor · actor:unc6993
GTIG's cluster designation for an LLMjacking actor: in mid-2026 it compromised a cloud instance through a misconfigured service-account key, used that access to reach an LLM API, ran a session-hijacking page posing as an application portal that had users paste a raw JSON payload holding an active access token, and used the open-source new-api and gcli2api gateways to pool and resell stolen model access (GTIG and Mandiant, 2026-11-02).
Defender insights
What each entry about UNC6993 tells a defender to do, newest first.
Story timeline
Hunting pivots
ATT&CK techniques (17 across 10 tactics)
17 techniques observed across 1 entry about this entity, derived from entry metadata and body evidence, never asserted without a published entry behind it · pinned to MITRE ATT&CK v20.1 · compare on the matrix · Navigator layer (JSON)
- Resource DevelopmentAcquire Infrastructure: Malvertising
- Initial AccessValid Accounts: Cloud Accounts · Exploit Public-Facing Application · Phishing
- PersistenceValid Accounts: Cloud Accounts · Account Manipulation: Additional Cloud Credentials · Account Manipulation: Additional Cloud Roles · Account Manipulation: SSH Authorized Keys · Create Account: Cloud Account
- Privilege EscalationValid Accounts: Cloud Accounts · Account Manipulation: Additional Cloud Credentials · Account Manipulation: Additional Cloud Roles · Account Manipulation: SSH Authorized Keys · Abuse Elevation Control Mechanism: Temporary Elevated Cloud Access
- StealthValid Accounts: Cloud Accounts
- Credential AccessSteal Application Access Token · Unsecured Credentials: Credentials In Files · Credentials from Password Stores: Cloud Secrets Management Stores
- DiscoveryCloud Infrastructure Discovery
- Lateral MovementUse Alternate Authentication Material: Application Access Token
- CollectionData from Information Repositories: Code Repositories · Data from Cloud Storage
- ImpactResource Hijacking: Cloud Service Hijacking
Resource Development TA0042
T1583.008Acquire Infrastructure: Malvertising×1
Adversaries may purchase online advertisements that can be abused to distribute malware to victims. Ads can be purchased to plant as well as favorably position artifacts in specific locations online, such as prominently placed within search engine results. These ads may make it more difficult for users to distinguish between actual search results and advertisements. Purchased ads may also target specific audiences using the advertising network’s capabilities, potentially further taking advantage of the trust inherently given to search engines and popular websites.
Evidence: 2026-11-09/llmjacking-stolen-cloud-keys-enable-model-services-resale · ATT&CK page ↗
Initial Access TA0001
T1078.004Valid Accounts: Cloud Accounts×1
Valid accounts in cloud environments may allow adversaries to perform actions to achieve Initial Access, Persistence, Privilege Escalation, or Defense Evasion. Cloud accounts are those created and configured by an organization for use by users, remote support, services, or for administration of resources within a cloud service provider or SaaS application. Cloud Accounts can exist solely in the cloud; alternatively, they may be hybrid-joined between on-premises systems and the cloud through syncing or federation with other identity sources such as Windows Active Directory.
Evidence: 2026-11-09/llmjacking-stolen-cloud-keys-enable-model-services-resale · ATT&CK page ↗
T1190Exploit Public-Facing Application×1
Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network. The weakness in the system can be a software bug, a temporary glitch, or a misconfiguration.
Evidence: 2026-11-09/llmjacking-stolen-cloud-keys-enable-model-services-resale · ATT&CK page ↗
T1566Phishing×1
Adversaries may send phishing messages to gain access to victim systems. All forms of phishing are electronically delivered social engineering. Phishing can be targeted, known as spearphishing. In spearphishing, a specific individual, company, or industry will be targeted by the adversary. More generally, adversaries can conduct non-targeted phishing, such as in mass malware spam campaigns.
Evidence: 2026-11-09/llmjacking-stolen-cloud-keys-enable-model-services-resale · ATT&CK page ↗
Persistence TA0003
T1078.004Valid Accounts: Cloud Accounts×1
Valid accounts in cloud environments may allow adversaries to perform actions to achieve Initial Access, Persistence, Privilege Escalation, or Defense Evasion. Cloud accounts are those created and configured by an organization for use by users, remote support, services, or for administration of resources within a cloud service provider or SaaS application. Cloud Accounts can exist solely in the cloud; alternatively, they may be hybrid-joined between on-premises systems and the cloud through syncing or federation with other identity sources such as Windows Active Directory.
Evidence: 2026-11-09/llmjacking-stolen-cloud-keys-enable-model-services-resale · ATT&CK page ↗
T1098.001Account Manipulation: Additional Cloud Credentials×1
Adversaries may add adversary-controlled credentials to a cloud account to maintain persistent access to victim accounts and instances within the environment.
Evidence: 2026-11-09/llmjacking-stolen-cloud-keys-enable-model-services-resale · ATT&CK page ↗
T1098.003Account Manipulation: Additional Cloud Roles×1
An adversary may add additional roles or permissions to an adversary-controlled cloud account to maintain persistent access to a tenant. For example, adversaries may update IAM policies in cloud-based environments or add a new global administrator in Office 365 environments. With sufficient permissions, a compromised account can gain almost unlimited access to data and settings (including the ability to reset the passwords of other admins).
Evidence: 2026-11-09/llmjacking-stolen-cloud-keys-enable-model-services-resale · ATT&CK page ↗
T1098.004Account Manipulation: SSH Authorized Keys×1
Adversaries may modify the SSH <code>authorized_keys</code> file to maintain persistence on a victim host. Linux distributions, macOS, and ESXi hypervisors commonly use key-based authentication to secure the authentication process of SSH sessions for remote management. The <code>authorized_keys</code> file in SSH specifies the SSH keys that can be used for logging into the user account for which the file is configured. This file is usually found in the user's home directory under <code><user-home>/.ssh/authorized_keys</code> (or, on ESXi, `/etc/ssh/keys-<username>/authorized_keys`). Users may edit the system’s SSH config file to modify the directives `PubkeyAuthentication` and `RSAAuthentication` to the value `yes` to ensure public key and RSA authentication are enabled, as well as modify the directive `PermitRootLogin` to the value `yes` to enable root authentication via SSH. The SSH config file is usually located under <code>/etc/ssh/sshd_config</code>.
Evidence: 2026-11-09/llmjacking-stolen-cloud-keys-enable-model-services-resale · ATT&CK page ↗
T1136.003Create Account: Cloud Account×1
Adversaries may create a cloud account to maintain access to victim systems. With a sufficient level of access, such accounts may be used to establish secondary credentialed access that does not require persistent remote access tools to be deployed on the system.
Evidence: 2026-11-09/llmjacking-stolen-cloud-keys-enable-model-services-resale · ATT&CK page ↗
Privilege Escalation TA0004
T1078.004Valid Accounts: Cloud Accounts×1
Valid accounts in cloud environments may allow adversaries to perform actions to achieve Initial Access, Persistence, Privilege Escalation, or Defense Evasion. Cloud accounts are those created and configured by an organization for use by users, remote support, services, or for administration of resources within a cloud service provider or SaaS application. Cloud Accounts can exist solely in the cloud; alternatively, they may be hybrid-joined between on-premises systems and the cloud through syncing or federation with other identity sources such as Windows Active Directory.
Evidence: 2026-11-09/llmjacking-stolen-cloud-keys-enable-model-services-resale · ATT&CK page ↗
T1098.001Account Manipulation: Additional Cloud Credentials×1
Adversaries may add adversary-controlled credentials to a cloud account to maintain persistent access to victim accounts and instances within the environment.
Evidence: 2026-11-09/llmjacking-stolen-cloud-keys-enable-model-services-resale · ATT&CK page ↗
T1098.003Account Manipulation: Additional Cloud Roles×1
An adversary may add additional roles or permissions to an adversary-controlled cloud account to maintain persistent access to a tenant. For example, adversaries may update IAM policies in cloud-based environments or add a new global administrator in Office 365 environments. With sufficient permissions, a compromised account can gain almost unlimited access to data and settings (including the ability to reset the passwords of other admins).
Evidence: 2026-11-09/llmjacking-stolen-cloud-keys-enable-model-services-resale · ATT&CK page ↗
T1098.004Account Manipulation: SSH Authorized Keys×1
Adversaries may modify the SSH <code>authorized_keys</code> file to maintain persistence on a victim host. Linux distributions, macOS, and ESXi hypervisors commonly use key-based authentication to secure the authentication process of SSH sessions for remote management. The <code>authorized_keys</code> file in SSH specifies the SSH keys that can be used for logging into the user account for which the file is configured. This file is usually found in the user's home directory under <code><user-home>/.ssh/authorized_keys</code> (or, on ESXi, `/etc/ssh/keys-<username>/authorized_keys`). Users may edit the system’s SSH config file to modify the directives `PubkeyAuthentication` and `RSAAuthentication` to the value `yes` to ensure public key and RSA authentication are enabled, as well as modify the directive `PermitRootLogin` to the value `yes` to enable root authentication via SSH. The SSH config file is usually located under <code>/etc/ssh/sshd_config</code>.
Evidence: 2026-11-09/llmjacking-stolen-cloud-keys-enable-model-services-resale · ATT&CK page ↗
T1548.005Abuse Elevation Control Mechanism: Temporary Elevated Cloud Access×1
Adversaries may abuse permission configurations that allow them to gain temporarily elevated access to cloud resources. Many cloud environments allow administrators to grant user or service accounts permission to request just-in-time access to roles, impersonate other accounts, pass roles onto resources and services, or otherwise gain short-term access to a set of privileges that may be distinct from their own.
Evidence: 2026-11-09/llmjacking-stolen-cloud-keys-enable-model-services-resale · ATT&CK page ↗
Stealth TA0005
T1078.004Valid Accounts: Cloud Accounts×1
Valid accounts in cloud environments may allow adversaries to perform actions to achieve Initial Access, Persistence, Privilege Escalation, or Defense Evasion. Cloud accounts are those created and configured by an organization for use by users, remote support, services, or for administration of resources within a cloud service provider or SaaS application. Cloud Accounts can exist solely in the cloud; alternatively, they may be hybrid-joined between on-premises systems and the cloud through syncing or federation with other identity sources such as Windows Active Directory.
Evidence: 2026-11-09/llmjacking-stolen-cloud-keys-enable-model-services-resale · ATT&CK page ↗
Credential Access TA0006
T1528Steal Application Access Token×1
Adversaries can steal application access tokens as a means of acquiring credentials to access remote systems and resources.
Evidence: 2026-11-09/llmjacking-stolen-cloud-keys-enable-model-services-resale · ATT&CK page ↗
T1552.001Unsecured Credentials: Credentials In Files×1
Adversaries may search local file systems and remote file shares for files containing insecurely stored credentials. These can be files created by users to store their own credentials, shared credential stores for a group of individuals, configuration files containing passwords for a system or service, or source code/binary files containing embedded passwords.
Evidence: 2026-11-09/llmjacking-stolen-cloud-keys-enable-model-services-resale · ATT&CK page ↗
T1555.006Credentials from Password Stores: Cloud Secrets Management Stores×1
Adversaries may acquire credentials from cloud-native secret management solutions such as AWS Secrets Manager, GCP Secret Manager, Azure Key Vault, and Terraform Vault.
Evidence: 2026-11-09/llmjacking-stolen-cloud-keys-enable-model-services-resale · ATT&CK page ↗
Discovery TA0007
T1580Cloud Infrastructure Discovery×1
An adversary may attempt to discover infrastructure and resources that are available within an infrastructure-as-a-service (IaaS) environment. This includes compute service resources such as instances, virtual machines, and snapshots as well as resources of other services including the storage and database services.
Evidence: 2026-11-09/llmjacking-stolen-cloud-keys-enable-model-services-resale · ATT&CK page ↗
Lateral Movement TA0008
T1550.001Use Alternate Authentication Material: Application Access Token×1
Adversaries may use stolen application access tokens to bypass the typical authentication process and access restricted accounts, information, or services on remote systems. These tokens are typically stolen from users or services and used in lieu of login credentials.
Evidence: 2026-11-09/llmjacking-stolen-cloud-keys-enable-model-services-resale · ATT&CK page ↗
Collection TA0009
T1213.003Data from Information Repositories: Code Repositories×1
Adversaries may leverage code repositories to collect valuable information. Code repositories are tools/services that store source code and automate software builds. They may be hosted internally or privately on third party sites such as Github, GitLab, SourceForge, and BitBucket. Users typically interact with code repositories through a web application or command-line utilities such as git.
Evidence: 2026-11-09/llmjacking-stolen-cloud-keys-enable-model-services-resale · ATT&CK page ↗
T1530Data from Cloud Storage×1
Adversaries may access data from cloud storage.
Evidence: 2026-11-09/llmjacking-stolen-cloud-keys-enable-model-services-resale · ATT&CK page ↗
Impact TA0040
T1496.004Resource Hijacking: Cloud Service Hijacking×1
Adversaries may leverage compromised software-as-a-service (SaaS) applications to complete resource-intensive tasks, which may impact hosted service availability.
Evidence: 2026-11-09/llmjacking-stolen-cloud-keys-enable-model-services-resale · ATT&CK page ↗
Entries about UNC6993 (1)
Co-occurring entities
Derived: referenced by the same focused operational entries (weekly summaries and report roundups don't count); ×N counts the shared entries.
Where this entity is cited
Source distribution
- cloud.google.com1 (33%)
- securitylabs.datadoghq.com1 (33%)
- threats.wiz.io1 (33%)
All cited sources (3)
- cloud.google.comGoogle Threat Intelligence Group and Mandianthttps://cloud.google.com/blog/topics/threat-intelligence/llmjacking-monetizing-compromised-cloud-models
- securitylabs.datadoghq.comDatadog Security Labshttps://securitylabs.datadoghq.com/articles/beyond-valid-credentials-how-exposed-aws-keys-are-tested-for-amazon-bedrock-access/
- threats.wiz.ioWiz (Cloud Threat Landscape)https://threats.wiz.io/all-incidents/threat-actors-targeting-gcp-billing-accounts-for-llm-usage