AI Security Research Portal
sourceactiveSources

Raw News Batch Ingest

This batch source note catalogs 34 raw news markdown sources currently present under vault/01-Raw-Sources/news/. The raw files remain immutable; this note is the durable ingest handle used by wiki pages, claims, and research questions.

Batch Analysis

Source Catalog

TitleKindDateTagsRaw
InkJect: The Visual Prompt Injection That Text Defenses Were Never Built to Stopindustry_blog2026-07-01ai-security, indirect-prompt-injection, multimodal-agent, visual-prompt-injection, vlmraw
Securing AI Agents with Cisco AI Defenseofficial_vendor_blog2026-06-29ai-agent-security, guardrails, mcp, prompt-injection, runtime-protectionraw
OpenAI limits its latest ChatGPT product to Trump-approved customers during cybersecurity reviewnews2026-06-26cyber-capability, frontier-models, governance, phased-releaseraw
MCP Auto-Execution: From Git Clone to Cloud Compromise in Amazon Q VS Code Extensionindustry_blog2026-06-26amazon-q, coding-agent, credential-theft, cve-2026-12957, mcp, workspace-trustraw
Exclusive: Gottheimer and Moolenaar roll out AI cloud security billnews2026-06-26cloud-compute, misuse-detection, model-development, policyraw
More Malicious OpenClaw Skills Threaten AI Supply Chainnews2026-06-25agentic-ai, ai-security, malicious-skills, news, openclaw, supply-chainraw
Latest AI Security Collection 2026-06-25collection_manifest2026-06-25agentic-ai, ai-for-security, ai-security, collection-manifest, latest, mcpraw
Chinese cybersecurity company 360 unveils “China's version of Mythos”, and Yitianzhen, to automate cnews2026-06-25automated-defense, cyber-model, dual-use, vulnerability-discoveryraw
Introducing computer use in Gemini 3.5 Flashofficial_blog2026-06-24agent-security, computer-use, gemini-3-5-flash, prompt-injectionraw
Behind the Curtain: Global AI warsnews2026-06-24ai-security, cyber-capability, five-eyes, frontier-ai, geopolitics, newsraw
Anthropic accuses Alibaba of running the largest distillation campaign yet against Claudenews2026-06-24ai-security, alibaba, claude, model-distillation, model-extraction, qwenraw
macOS.Gaslight - Rust Backdoor Turns Prompt Injection on the Analyst, Not the Sandboxindustry_blog2026-06-23ai-security, dprk, macos, malware-analysis, prompt-injectionraw
GLM 5.2 on CyberBT-CTF: The strongest open source contender to Anthropic/OpenAI we have testedindustry_blog2026-06-23ai-security, cyber-benchmarks, glm-5-2, model-distillation, open-weight-modelsraw
We have Mythos at Home: GLM 5.2 beats Claude in our Cyber Benchmarksindustry_blog2026-06-22ai-security, cyber-benchmarks, glm-5-2, idor, vulnerability-detectionraw
AutoJack: How a single page can RCE the host running your AI agentsecurity_blog2026-06-19agent-security, autogen-studio, localhost, mcp, rce, websocketraw
AI Security News Collection 2026-06-19collection_manifest2026-06-19ai-security, collection, news, trend-monitoringraw
Securing the future of AI agentsresearch_blog2026-06-18agent-security, ai-control, defense-in-depth, insider-threat, monitoringraw
From package to postinstall payload: Inside the Mastra npm supply chain compromise by Sapphire Sleetsecurity_blog2026-06-18ci-cd, credential-theft, mastra, npm, postinstall, supply-chainraw
Build your own vulnerability harnessblog2026-06-18agent-orchestration, ai-for-security, validation, vulnerability-discoveryraw
Duo Brings Identity and Authorization Across AI Agent Gatewaysofficial_blog2026-06-17agent-identity, ai-gateway, authorization, mcp, non-human-identity, security-for-airaw
AWS Security Agent adds threat modeling, Kiro power and Claude Code plugin, and moreofficial_blog2026-06-17ai-for-security, code-review, coding-agents, mcp, security-agent, strideraw
AI Agent Identity and Permission Challenges: How Uber and Auth0 Are Rethinking Access Controlnews2026-06-17agent-identity, delegated-authority, mcp, multi-agent, oauth, security-for-airaw
Securing the Agentic AI Frontier: Palo Alto Networks and Databricks Deliver a New Standard for AI Seofficial_blog2026-06-16agentic-ai, ai-gateway, data-security, governance, mcp, runtime-securityraw
Pickle in the Middle - Hijacking Vertex AI Model Uploads for Cross-Tenant RCEsecurity_blog2026-06-16bucket-squatting, cloud-security, model-artifact, pickle, rce, vertex-airaw
Anthropic AI dispute sparks concerns about U.S. cybersecurity defensesnews2026-06-16Axios, ai-for-security, cyber-defense, model-capability, news, policyraw
Arcade Raises $60M to Become the Secure Action Layer Behind Every Production AI Agentpress_release2026-06-15agent-authorization, auditability, governance, market-signal, mcp, security-for-airaw
When Your AI Agent's Memory Becomes a Security Liabilityincident_report2026-06-11agent-memory, checkpointer, deserialization, langgraph, rce, security-for-airaw
Prompt injection still drives most agentic AI security failures in productionnews2026-06-11agentic-ai, coding-agents, incidents, owasp, prompt-injection, security-for-airaw
CISA Tells US Agencies to Fix Security Bugs in as Little as 3 Days Thanks to AI Threatsnews2026-06-11WIRED, ai-threats, government, news, security-for-ai, vulnerability-managementraw
The Meta hack shows there's more to AI security than Mythosnews2026-06-05account-recovery, account-takeover, ai-agent, identity-verification, incident, security-for-airaw
Microsoft's open-source SkillOpt automatically upgrades AI agent skills without touching model weighnews2026-06agent-skills, microsoft, news, self-evolving-agents, skilloptraw
AI Cyber Challenge marks pivotal inflection point for cyber defensenews2025-08DARPA, ai-cyber-challenge, ai-for-security, ai-security, patching, vulnerability-discoveryraw
AI Agents Are Getting Better at Writing Code—and Hacking It as Wellnews2025-06-25Will Knight, ai-agents, cyber-capability, cybergym, dual-use, newsraw
Generative AI's Biggest Security Flaw Is Not Easy to Fixnews2023-04WIRED, ai-security, industry-risk, journalism, prompt-injectionraw