Post

Interesting how the last 8 months shifted AI security from simple prompt abuse to full-blown agentic warfare. 🧵👇 #AI #AgentsAI

Raúl Ferrer

@raulferrer.dev

12 Sept

Anthropic’s latest Threat Intelligence Report (Dec 2025 – Aug 2026) breaks down how threat actors are pushing Claude past basic assistance into autonomous execution: www.anthropic.com/threat-intel...

anthropic.comCountering misuse of AI: September 2026 / AnthropicCase studies from threat actors disrupted between December 2025 and August 2026 across seven areas of harm, from cyber operations to biological misuse.

Raúl Ferrer

@raulferrer.dev

12 Sept

>>> AI-Augmented Cyber Ops: Bad actors aren't just asking for code anymore—they're orchestrating multi-agent swarms for active recon, zero-day discovery, and self-adapting malware.

Raúl Ferrer

@raulferrer.dev

12 Sept

>>> Autonomous Influence Networks: Automated sockpuppet fleets using deep target profiling to scale precision disinformation campaigns.

Raúl Ferrer

@raulferrer.dev

12 Sept

>>> Illicit Model Distillation: Industrial-scale extraction pipelines harvesting Claude’s outputs to train rival models on the sly.

Raúl Ferrer

@raulferrer.dev

>>> Surveillance & Arms Risks: State-linked actors attempting to integrate AI into activist monitoring and autonomous hardware workflows.

12/9/26, 7:02 am0 reposts0 likes

Raúl Ferrer

@raulferrer.dev

12 Sept

Were you already familiar with this report? What do you think about this transition toward agentic attacks? Let me know in the comments.