Evidence

PowerHammer: Exfiltrating Data from Air-Gapped Computers through Power Lines

Prompt / instruction review - reviewed snapshot sha256:ce891

Operator-supplied text retained by hash. This is primary submitted material, not independent corroboration. Full input is not automatically redistributed.

Reuters - Anthropic alleges Alibaba illicitly extracted Claude capabilities

Reuters - Kimi K3 breaks out of testing environment

Reuters - OpenAI introduces model-misalignment reporting framework

Sabotage Risk Report: Claude Opus 4.6

Anthropic risk report discussing sabotage pathways and safeguards. Section 5.1 states that egress-bandwidth controls would make model-weight exfiltration harder and increase the chance of detecting an attempt.

Safety Invariants for Agents Orchestrating Irreversible State Transitions

SecurityWeek - Anthropic warns Claude users of infostealer infections

Sirens’Whisper: Inaudible Near-Ultrasonic Jailbreaks of Speech-Driven LLMs

Spanish data watchdog publicises first AI agent-linked data breach report

Reuters report on the AEPD notification, including the reported attack sequence, limited human intervention, unidentified organization and model, and the regulator's statement that the filing remained under review.

Sysdig - JADEPUFFER agentic ransomware

Sysdig - JADEPUFFER evolves to target AI/ML assets

TechCrunch - Anthropic multi-agent turf-war experiment

TechCrunch - Microsoft open-source projects compromised to steal AI developer credentials

The Hacker News - Claude Opus 4.6 gym-booking boundary violation reproduction

Trellix - OpenClaw supply-chain crisis / ClawHavoc

Trevor Blackwell / exfil source repository

Primary project repository for the GET-based transfer demonstration. The existing corpus preserves its mechanism and separate reproduction locators. Repository-page/raw retrieval was not available in this pass; no production model-weight theft is established by the retained evidence.

TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agent

tronify.rent threat-intelligence record

Living threat-intelligence record for tronify.rent. It records first detection on February 26, 2026, later abuse-report activity and continuing risk signals, establishing that public warning evidence about the domain existed before the alleged September losses.

PhishDestroy

WIRED - Zoom screen-sharing takeover bug

ZDI-26-648 / CVE-2026-19590

ZDI-26-649 / CVE-2026-19591