AgentsCrowdStrike 2026 Global Threat Report AI Attacks Up 89%CrowdStrike·high signalAI-enabled adversary ops up 89% YoY. Fastest breakout 27 seconds. DeepSeek-R1 produces 50% more vulnerable code on politically sensitive prompts. 90+ orgs exploited via prompt injection.SourceSource pageCrowdStrike↳ Follow the threadPolicy dependency / Stack layerHalluSquatting weaponizes LLM hallucinations to push botnet malware into agentsThe Hacker NewsPolicy dependency / Stack layerPrismata Confines Cross-Site Prompt Injection by Treating Web Agents Like an XSS ProblemarXivStack layer / Threat patternAsk HN: 'Another Hacker News With Less AI and More Human-Focused Hacking News?'Hacker NewsPolicy dependency / Stack layerPattern: Safety Rails Are Migrating From the Prompt Into the Harness's Auto ModeClaude Code ChangelogStack layer / Threat patternMid-Session Tool Injection weaponized against WebMCP agents via threshold poisoning and fake diagnostic eventsAdversa AIStack layer / Threat patternsickn33/agentic-awesome-skills Hits 1,900+ Installable Agent Skills — and an Installer CLI to MatchGitHubStack layer / Threat patternCodeTracer Performs Forensic Attribution of Backdoored Code CompletionsarXivStack layer / Threat patternThursdAI, July 9: OpenAI Claims Sol Autonomously Post-Trained LunaThursdAI (Alex Volkov)