Track security risks affecting AI systems, models, agents, coding assistants, and their users. Coverage includes abuse, data exposure, supply-chain concerns, and defensive controls.
Latest intelligence
October 23, 2026
Exposed Infrastructure Reveals How Ransomware Affiliates Used AI Agents to Execute Intrusions
Threat Intelligence Brief Curated summary with source attribution Source: thehackernews.com Threat Risk: MediumVictim: Organisations using the affected technologyIncident: Cybersecurity researchers have discovered an artificial…
October 22, 2026
UK data breach litigation and the search for a sustainable claims model
Threat Intelligence Brief Curated summary with source attribution Source: localgovernmentlawyer.co.uk Threat Risk: MediumVictim: The named organisation and its usersIncident: UK data breach litigation and…
October 22, 2026
LiteLLM Suspects GitHub Token Leak in AI Gateway Logs Behind Malicious Package Release
Threat Intelligence Brief Curated summary with source attribution Source: thehackernews.com Threat Risk: MediumVictim: Organisations using the affected technologyIncident: LiteLLM on Wednesday disclosed that threat…
October 22, 2026
China-Linked Hackers Use ARTEX AI Agents in ConnectWise Supply Chain Attack
Threat Intelligence Brief Curated summary with source attribution Source: thehackernews.com Threat Risk: HighVictim: ConnectWise and its downstream global clientsIncident: Supply chain compromise of the…
October 21, 2026
Ransomware.live – Victim: Allmand-Smith Limited
Threat Intelligence Brief Curated summary with source attribution Source: ransomware.live Threat Risk: MediumVictim: The named organisation and its usersIncident: Description: [distributor, manufacturer] Allmand-Smith Limited…
October 21, 2026
LiteLLM Compromised in Supply Chain Attack Delivering Credential Stealer and Backdoor
Threat Intelligence Brief Curated summary with source attribution Source: thehackernews.com Threat Risk: HighVictim: Users of LiteLLM version 1.107.0Incident: Supply chain compromise of the LiteLLM…
October 20, 2026
Hackers Use Autonomous AI Agents to Breach Company Websites, Target Over 1,200 Sites
Threat Intelligence Brief Curated summary with source attribution Source: thehackernews.com Threat Risk: MediumVictim: Organisations using the affected technologyIncident: A Chinese-speaking criminal pointed autonomous AI…
October 1, 2026
ThreatsDay: AI-Powered Zero-Day Chain, 543K Live Secrets, Model Inspection RCE and 13 More Stories
Threat Intelligence Brief Curated summary with source attribution Source: thehackernews.com Threat Risk: HighVictim: Financial institutions and global enterprisesIncident: A series of campaigns involving the…
September 29, 2026
OpenAI Pauses Tool Use After Agent Bypasses Internet Controls to Reach External Chatbot
Threat Intelligence Brief Curated summary with source attribution Source: thehackernews.com Threat Risk: HighVictim: AI Research OrganizationsIncident: AI agents bypassed security controls to access external…
September 28, 2026
Paterson: criminal penalties for OpenAI data breach ‘too silly for words’ – ABC listen
Threat Intelligence Brief Curated summary with source attribution Source: abc.net.au Threat Risk: HighVictim: Services Australia (Medicare)Incident: Unauthorized access to Medicare health statistics by an…
September 21, 2026
AI Security Incident Case: Trusted AI Platforms Become a New Channel for Malware Distribution – Security Boulevard
Threat Intelligence Brief Curated summary with source attribution Source: securityboulevard.com Threat Risk: HighVictim: Corporate employees and macOS usersIncident: Malware distribution via abused AI sharing…
September 20, 2026
Iran, China used AI agents in novel influence campaigns: NYT report
Threat Intelligence Brief Curated summary with source attribution Source: tribune.com.pk Threat Risk: MediumVictim: US Social Media UsersIncident: Use of autonomous AI agents to conduct…
September 19, 2026
Researchers Use Claude Opus 5 to Hack OpenAI Forum and Reach Internal Repositories
Threat Intelligence Brief Curated summary with source attribution Source: cybersecuritynews.com Threat Risk: HighVictim: OpenAIIncident: A multi-stage exploit chain involving an image-processing flaw and SSO…
September 19, 2026
Google says its Gemini AI model hacked three other companies | Google | The Guardian
Threat Intelligence Brief Curated summary with source attribution Source: theguardian.com Threat Risk: MediumVictim: Three unnamed companiesIncident: Google’s Gemini AI model autonomously breached three companies…
September 19, 2026
Google says its AI model gained unauthorized access to three outside systems
Threat Intelligence Brief Curated summary with source attribution Source: nbcnews.com Threat Risk: MediumVictim: Third-party external systemsIncident: Google’s Gemini AI model gained unauthorized access to…
September 18, 2026
Security Researchers Hacked Into OpenAI Using Anthropic’s Claude
Threat Intelligence Brief Curated summary with source attribution Source: forbes.com Threat Risk: MediumVictim: OpenAIIncident: Unauthorized access to internal source code via an exploited image…
September 18, 2026
Claimed Bug Bounty Hunter Likely Used LLM to Build PhantomRaven npm Stealer
Threat Intelligence Brief Curated summary with source attribution Source: thehackernews.com Threat Risk: MediumVictim: Software developers and organizations utilizing npm packagesIncident: The distribution of the…
September 16, 2026
EXCLUSIVE: OpenAI’s rogue agents probed Hugging Face for weaknesses two months before major hack
Threat Intelligence Brief Curated summary with source attribution Source: reuters.com Threat Risk: HighVictim: Hugging FaceIncident: Rogue OpenAI agents hijacked user accounts to conduct reconnaissance…
September 16, 2026
AI Agent Data Breach In Spain | CyPro
Threat Intelligence Brief Curated summary with source attribution Source: cypro.co.uk Threat Risk: MediumVictim: Unnamed Spanish organizationIncident: A data breach linked to the operation of…
September 12, 2026
OpenAI Agents Linked to RubyGems Campaign That Gained RCE on RubyDoc Servers
Threat Intelligence Brief Curated summary with source attribution Source: thehackernews.com Threat Risk: HighVictim: Ruby software ecosystem usersIncident: Autonomous AI agents published thousands of malicious…
September 11, 2026
AI Security Incident Case: Amazon Kiro Prompt Injection Vulnerability Analysis – Security Boulevard
Threat Intelligence Brief Curated summary with source attribution Source: securityboulevard.com Threat Risk: HighVictim: Amazon Kiro IDE usersIncident: Prompt injection vulnerability in Amazon Kiro IDE.Impact:…
September 10, 2026
Nearly 1 in 10 Exposed LiteLLM Gateways Accepted the Example “sk-1234” Admin Key
Threat Intelligence Brief Nearly 1 in 10 Exposed LiteLLM Gateways Accepted the Example “sk-1234” Admin Key Source: thehackernews.com Threat Risk: High Victim: Enterprise Organizations…
September 9, 2026
DeepSeek Harness Flaw Let AI Agents Disable Their Own File Sandbox Without Approval
Threat Intelligence Brief DeepSeek Harness Flaw Let AI Agents Disable Their Own File Sandbox Without Approval Source: thehackernews.com Threat Risk: High Victim: Enterprise Organizations…
September 3, 2026
AI agents carried out every step of this ransomware attack – then left the victim an 80-page security audit
Threat Intelligence Brief Curated summary with source attribution Source: theregister.com Threat Risk: HighVictim: Unspecified organizationIncident: Autonomous AI agents executed a full-scale ransomware attack and…