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 count: 34
- Dominant operation: batch ingest from raw captures into wiki synthesis.
- Evidence quality: mixed. Treat papers and standards as stronger evidence than news and vendor reports; treat collection manifests as routing aids, not direct evidence.
- Citation status: raw paper captures include bibliographic metadata when available, but canonical DOI/arXiv verification should be refreshed for sources promoted into claims or reports.
Source Catalog
| Title | Kind | Date | Tags | Raw |
|---|---|---|---|---|
| InkJect: The Visual Prompt Injection That Text Defenses Were Never Built to Stop | industry_blog | 2026-07-01 | ai-security, indirect-prompt-injection, multimodal-agent, visual-prompt-injection, vlm | raw |
| Securing AI Agents with Cisco AI Defense | official_vendor_blog | 2026-06-29 | ai-agent-security, guardrails, mcp, prompt-injection, runtime-protection | raw |
| OpenAI limits its latest ChatGPT product to Trump-approved customers during cybersecurity review | news | 2026-06-26 | cyber-capability, frontier-models, governance, phased-release | raw |
| MCP Auto-Execution: From Git Clone to Cloud Compromise in Amazon Q VS Code Extension | industry_blog | 2026-06-26 | amazon-q, coding-agent, credential-theft, cve-2026-12957, mcp, workspace-trust | raw |
| Exclusive: Gottheimer and Moolenaar roll out AI cloud security bill | news | 2026-06-26 | cloud-compute, misuse-detection, model-development, policy | raw |
| More Malicious OpenClaw Skills Threaten AI Supply Chain | news | 2026-06-25 | agentic-ai, ai-security, malicious-skills, news, openclaw, supply-chain | raw |
| Latest AI Security Collection 2026-06-25 | collection_manifest | 2026-06-25 | agentic-ai, ai-for-security, ai-security, collection-manifest, latest, mcp | raw |
| Chinese cybersecurity company 360 unveils “China's version of Mythos”, and Yitianzhen, to automate c | news | 2026-06-25 | automated-defense, cyber-model, dual-use, vulnerability-discovery | raw |
| Introducing computer use in Gemini 3.5 Flash | official_blog | 2026-06-24 | agent-security, computer-use, gemini-3-5-flash, prompt-injection | raw |
| Behind the Curtain: Global AI wars | news | 2026-06-24 | ai-security, cyber-capability, five-eyes, frontier-ai, geopolitics, news | raw |
| Anthropic accuses Alibaba of running the largest distillation campaign yet against Claude | news | 2026-06-24 | ai-security, alibaba, claude, model-distillation, model-extraction, qwen | raw |
| macOS.Gaslight - Rust Backdoor Turns Prompt Injection on the Analyst, Not the Sandbox | industry_blog | 2026-06-23 | ai-security, dprk, macos, malware-analysis, prompt-injection | raw |
| GLM 5.2 on CyberBT-CTF: The strongest open source contender to Anthropic/OpenAI we have tested | industry_blog | 2026-06-23 | ai-security, cyber-benchmarks, glm-5-2, model-distillation, open-weight-models | raw |
| We have Mythos at Home: GLM 5.2 beats Claude in our Cyber Benchmarks | industry_blog | 2026-06-22 | ai-security, cyber-benchmarks, glm-5-2, idor, vulnerability-detection | raw |
| AutoJack: How a single page can RCE the host running your AI agent | security_blog | 2026-06-19 | agent-security, autogen-studio, localhost, mcp, rce, websocket | raw |
| AI Security News Collection 2026-06-19 | collection_manifest | 2026-06-19 | ai-security, collection, news, trend-monitoring | raw |
| Securing the future of AI agents | research_blog | 2026-06-18 | agent-security, ai-control, defense-in-depth, insider-threat, monitoring | raw |
| From package to postinstall payload: Inside the Mastra npm supply chain compromise by Sapphire Sleet | security_blog | 2026-06-18 | ci-cd, credential-theft, mastra, npm, postinstall, supply-chain | raw |
| Build your own vulnerability harness | blog | 2026-06-18 | agent-orchestration, ai-for-security, validation, vulnerability-discovery | raw |
| Duo Brings Identity and Authorization Across AI Agent Gateways | official_blog | 2026-06-17 | agent-identity, ai-gateway, authorization, mcp, non-human-identity, security-for-ai | raw |
| AWS Security Agent adds threat modeling, Kiro power and Claude Code plugin, and more | official_blog | 2026-06-17 | ai-for-security, code-review, coding-agents, mcp, security-agent, stride | raw |
| AI Agent Identity and Permission Challenges: How Uber and Auth0 Are Rethinking Access Control | news | 2026-06-17 | agent-identity, delegated-authority, mcp, multi-agent, oauth, security-for-ai | raw |
| Securing the Agentic AI Frontier: Palo Alto Networks and Databricks Deliver a New Standard for AI Se | official_blog | 2026-06-16 | agentic-ai, ai-gateway, data-security, governance, mcp, runtime-security | raw |
| Pickle in the Middle - Hijacking Vertex AI Model Uploads for Cross-Tenant RCE | security_blog | 2026-06-16 | bucket-squatting, cloud-security, model-artifact, pickle, rce, vertex-ai | raw |
| Anthropic AI dispute sparks concerns about U.S. cybersecurity defenses | news | 2026-06-16 | Axios, ai-for-security, cyber-defense, model-capability, news, policy | raw |
| Arcade Raises $60M to Become the Secure Action Layer Behind Every Production AI Agent | press_release | 2026-06-15 | agent-authorization, auditability, governance, market-signal, mcp, security-for-ai | raw |
| When Your AI Agent's Memory Becomes a Security Liability | incident_report | 2026-06-11 | agent-memory, checkpointer, deserialization, langgraph, rce, security-for-ai | raw |
| Prompt injection still drives most agentic AI security failures in production | news | 2026-06-11 | agentic-ai, coding-agents, incidents, owasp, prompt-injection, security-for-ai | raw |
| CISA Tells US Agencies to Fix Security Bugs in as Little as 3 Days Thanks to AI Threats | news | 2026-06-11 | WIRED, ai-threats, government, news, security-for-ai, vulnerability-management | raw |
| The Meta hack shows there's more to AI security than Mythos | news | 2026-06-05 | account-recovery, account-takeover, ai-agent, identity-verification, incident, security-for-ai | raw |
| Microsoft's open-source SkillOpt automatically upgrades AI agent skills without touching model weigh | news | 2026-06 | agent-skills, microsoft, news, self-evolving-agents, skillopt | raw |
| AI Cyber Challenge marks pivotal inflection point for cyber defense | news | 2025-08 | DARPA, ai-cyber-challenge, ai-for-security, ai-security, patching, vulnerability-discovery | raw |
| AI Agents Are Getting Better at Writing Code—and Hacking It as Well | news | 2025-06-25 | Will Knight, ai-agents, cyber-capability, cybergym, dual-use, news | raw |
| Generative AI's Biggest Security Flaw Is Not Easy to Fix | news | 2023-04 | WIRED, ai-security, industry-risk, journalism, prompt-injection | raw |