The Latest Threat Research and Intelligence

Get the Latest Cybersecurity Research, Threat Intelligence, and AI Security Insights from SentinelLABS.

Subscribe Now
TraderTraitor_APIs_ftr

Don’t Call Us, We’ll Call Your APIs | TraderTraitor Backdoors Resurface on Victim With No Crypto Ties

North Korean operators built a foothold on a DevOps engineer's Mac in a campaign whose job interview lures deliver malware via Terraform lock files.

Read More
hf-agents_ftr

Agents at Large | Tracing Illicit OpenAI Agent Activity on Hugging Face

Two Hugging Face accounts reveal that OpenAI's agents staged relay code, internal probes and ChatGPT account registration beyond the published timeline.

Read More
model_is_malware_ftr

The Model Is the Malware | What Four Agentic Intrusions Tell Defenders

OpenAI, Anthropic and Meta disclosed agents reaching external systems. The tools didn't matter, and that changes the playbook for investigating intrusions.

Read More
Mythos_sol_ftr

Sol Searching | Can Frontier Models Tackle Autonomous Long-Horizon Malware Analysis?

A real-world benchmark tests whether powerful AI models can keep an investigation trustworthy when new evidence invalidates their conclusions.

Read More

All SentinelLABS Posts

  • Don’t Call Us, We’ll Call Your APIs | TraderTraitor Backdoors Resurface on Victim With No Crypto Ties
    LABScon
    Albert Priego18. Sept. 2026

    Don’t Call Us, We’ll Call Your APIs | TraderTraitor Backdoors Resurface on Victim With No Crypto Ties

    North Korean operators built a foothold on a DevOps engineer's Mac in a campaign whose job interview lures deliver malware via Terraform lock files.

  • Agents at Large | Tracing Illicit OpenAI Agent Activity on Hugging Face
    AI Research
    Tom Hegel16. Sept. 2026

    Agents at Large | Tracing Illicit OpenAI Agent Activity on Hugging Face

    Two Hugging Face accounts reveal that OpenAI's agents staged relay code, internal probes and ChatGPT account registration beyond the published timeline.

  • The Model Is the Malware | What Four Agentic Intrusions Tell Defenders
    AI Research
    Gabriel Bernadett-Shapiro13. Aug. 2026

    The Model Is the Malware | What Four Agentic Intrusions Tell Defenders

  • Sol Searching | Can Frontier Models Tackle Autonomous Long-Horizon Malware Analysis?
    AI Research
    Juan Andrés Guerrero-Saade22. Juli 2026

    Sol Searching | Can Frontier Models Tackle Autonomous Long-Horizon Malware Analysis?

  • Iran War Cyber Threat Landscape | A Midyear Assessment on What Matters
    Adversary
    Tom Hegel21. Juli 2026

    Iran War Cyber Threat Landscape | A Midyear Assessment on What Matters

  • Context Engineering | Compaction & Agent Memory for Automated Malware Analysis
    AI Research
    Gabriel Bernadett-Shapiro2. Juli 2026

    Context Engineering | Compaction & Agent Memory for Automated Malware Analysis

  • macOS.Gaslight | Rust Backdoor Turns Prompt Injection on the Analyst, Not the Sandbox
    Adversary
    Phil Stokes23. Juni 2026

    macOS.Gaslight | Rust Backdoor Turns Prompt Injection on the Analyst, Not the Sandbox

  • LABScon25 Replay | Keynote: Steps to an Ecology of Cyber
    LABScon
    LABScon11. Juni 2026

    LABScon25 Replay | Keynote: Steps to an Ecology of Cyber

  • LABScon25 Replay | Gamaredon x Turla: Unveiling a 2025 Espionage Alliance Targeting Ukraine
    LABScon
    LABScon2. Juni 2026

    LABScon25 Replay | Gamaredon x Turla: Unveiling a 2025 Espionage Alliance Targeting Ukraine

  • LABScon25 Replay | Breach Alpha: Trading on Cyber Fallout
    LABScon
    LABScon14. Mai 2026

    LABScon25 Replay | Breach Alpha: Trading on Cyber Fallout

  • PCPJack | Cloud Worm Evicts TeamPCP and Steals Credentials at Scale
    Crimeware
    Alex Delamotte7. Mai 2026

    PCPJack | Cloud Worm Evicts TeamPCP and Steals Credentials at Scale

  • LABScon25 Replay | Please Connect to the Foreign Entity to Enhance Your User Experience
    LABScon
    LABScon6. Mai 2026

    LABScon25 Replay | Please Connect to the Foreign Entity to Enhance Your User Experience