Papers Index

One summary page per research paper, vendor whitepaper, or industry survey. Source files (PDFs, web archives) live in .raw/papers/. Each paper page summarizes key claims, methodology, contradictions, and what it supports.

Pages

• 1.8M Prompts, 30 Alerts — Source: Unprompted Conference 2026, Stage 2 Lecture 08 (Matt Rittinghouse + Millie Rittinghouse, Salesforce Cybersecurity Operations Cent…
• ADR: Agentic Detection for Enterprise AI — Source: arXiv:2605.17380 — ADR: An Agentic Detection System for Enterprise Agentic AI Security (submi…
• AgentShield: Security Auditor for AI Agents — Source: GitHub — affaan-m/agentshield (README fetched 2026-05-15).
• AI Agents Are Here. So Are the Threats. — Source: Unit 42 — AI Agents Are Here. So Are the Threats. (2025-05-01) by Jay…
• AI-Augmented SOC Survey — AI-Augmented SOC: A Survey of LLMs and Agents for Security Automation (Srinivas, Kirk, Zendejas, Espino, Boskovich, Bari, Dajani, Alzahra…
• Exploring the AI Automation Boundary for Threat Hunting — A practitioner talk by Arthi Nagarajan (Datadog) at Unprompted (March 2026), on applying AI to threat hunting across large, schema-divers…
• AI Coding Agent Governance — Source: Knostic — AI Coding Agent Governance (2026, undated post).
• AI Cybersecurity After Mythos: The Jagged Frontier — A blog post by Stanislav Fort (Founder and Chief Scientist, AISLE) responding to Anthropic’s Claude Mythos / Project Glasswing announcement.
• AI Data Security — Source: Knostic — AI Data Security (2026).
• The AI Security Larsen Effect — A practitioner talk by Maxim Kovalsky of Consortium Networks, a value-added reseller (VAR), at the March 2026 Unprompted Conference.
• AI Security Standards: Agentic Threats Outpace Frameworks — Source: wiki-internal working paper (no external URL).
• AISLE: 12 of 12 OpenSSL Vulnerabilities — Source:…
• Agentic Coding Trends Report — Source:…
• Frontier Red Team Vulnerability Research — Sources: 0-days (Feb 5, 2026) ·…
• Project Glasswing: Securing Critical Software — Source: Anthropic, Project Glasswing (May 12, 2026).
• Project Glasswing: Initial Update — Source: Anthropic — Project Glasswing: An initial update (May 22, 2026).
• Agentic AI Security Scoping Matrix — The AWS Security Blog post that introduced the Agentic AI Security Scoping Matrix on 2025-11-21.
• Beyond the Chatbot: Delivering an Agentic SOC — Source: Conference abstracts page · Conference agenda
• AI Fingerprints for Threat Detection — A practitioner talk by Natalie Isak and Waris Gill (Microsoft) at the Unprompted Conference (March 2026) on BinaryShield.
• Breaking the Lethal Trifecta (Without Ruining Your Agents) — This page combines two source artifacts: the slides (13 frames; data + diagrams + the actual ToolAnnotations API) and the speaker trans…
• Building Secure Agentic Systems — Source: Unprompted Conference 2026, Stage 1 Lecture 06 (Brooks McMillin, Dropbox).
• Capability-Based Authorization for AI Agents
• Claude Code Security Announcement — Source:…
• Partners Putting Opus to Work for Cybersecurity — Source:…
• Codex Security Announcement — Source: OpenAI blog — Introducing Aardvark (fetched 2026-05-15).
• Detection & Deception Engineering in the Matrix (Orbie) — A practitioner talk by Bob Rudis and Glenn Thorpe (GreyNoise) at Unprompted (March 2026) on Orbie, an AI agent that operates over interne…
• Emerging Cybersecurity Practices for Agentic AI Applications — Source: Anton Goncharov, original research (March 2026).
• FIRST Vulnerability Forecast — Source: FIRST — Vulnerability Forecast for 2026 (2026-02-11).
• GenAI Endpoint Observability for Detection Engineers — A practitioner talk by Mika Ayenson, who leads Threat Research and Detection Engineering at Elastic, delivered at the March 2026 Unprompt…
• Glass-Box Security: Interpretability for AI Defense — Source: Unprompted Conference 2026, Stage 2 Lecture 10 (Carl Hurd, Starseer).
• Google Project Zero — Source: Project Zero — From Naptime to Big Sleep (October 31, 2024).
• CodeMender: AI Agent for Code Security — Source:…
• Gartner Market Guide for Guardian Agents — Source:…
• Guardrails Beyond Vibes: Shipping Security Agents — Source: Unprompted Conference 2026, Stage 1 Lecture 05 (Jeffrey Zhang + Siddh Shah, Stripe).
• Hooking Coding Agents with Cedar — Source: Conference-only materials — slides PDF + audio-transcript via attendee Google Drive share.
• Software Supply Chain Security State of the Union — JFrog’s annual report on the state of the software supply chain, built on three inputs: JFrog Platform telemetry (the platform held 18.2…
• LlamaFirewall Guardrail Paper — Source paper for LlamaFirewall, Meta’s open-source agent guardrail framework: “LlamaFirewall: An open source guardrail system for buildin…
• Securing Agentic AI Systems: A Multilayer Framework — The arXiv preprint that introduced the MAAIS framework (2025-12-19).
• Continuous Detection and Continuous Response — A vendor framing piece by Asaf Wiener (co-founder and CEO, Mate Security), May 2026, introducing an architectural framework the company c…
• MDASH: Defense at AI Speed — Source:…
• Measuring Security-Agent Effectiveness — A practitioner talk by Joshua Saxe at the March 2026 Unprompted Conference.
• Entra Agent ID: Security and Governance Model — Two Microsoft Learn overview docs define the identity-control-plane model behind Microsoft Entra Agent ID: a security overview (why AI sy…
• Microsoft SDL — Microsoft Security Blog post — Yonatan Zunger, 2026-02-03 — announces the explicit extension of Microsoft’s Secure Development Lifecycle…
• Secure Agentic AI End-to-End — Vasu Jakkal’s pre-RSAC 2026 announcement post (2026-03-20) consolidating Microsoft’s agentic-AI security product roadmap across Microsoft…
• MOAK: Autonomous AI Exploit Pipeline — Source: MOAK blog, April 9, 2026.
• Mother of All KEVs (MOAK origin story) — Launch announcement and origin story for the MOAK Engine, published April 9, 2026 by Niv Hoffman, Ofir Eisenberg, and Yair Saban at moak.ai.
• Mythos-Ready Security Program — Source: The “AI Vulnerability Storm”: Building a “Mythos-ready” Security Program — Expedited Strategy Briefing (Cloud Security Alliance C…
• AI Supply Chain Risks and Mitigations
• OpenAnt: LLM-Based Vulnerability Discovery — Source: Knostic blog — Introducing OpenAnt (fetched 2026-05-15).
• OSINT to Knowledge Graph for Threat Intel — A practitioner talk by Dongdong Sun, a machine-learning engineer on threat intelligence at Palo Alto Networks, at the March 2026 Unprompt…
• OWASP Agentic AI Threats and Mitigations — Source:…
• State of Agentic AI Security and Governance — Source:…
• Agentic SDLC in Practice — Source:…
• Enterprise Patch and Remediation Benchmark — A vendor benchmark built on anonymized remediation telemetry from global enterprise environments over twelve months.
• Rethinking Security Agent Evaluation — A practitioner talk by Mudita Khurana (Airbnb) at Unprompted (March 2026) arguing that security-agent evaluation is rooted in too-narrow,…
• Secure AI Framework Approach — Google’s 11-page practitioner-facing implementation guide for SAIF (the Secure AI Framework).
• Scaling Agentic AI: A Leadership Guide for CIOs — Source: Gartner webinar (Bizzabo-streamed, 60 min).
• Securing the Autonomous Future — Source:…
• Securing Workspace GenAI at Google — Source: Unprompted Conference 2026, Stage 1 Lecture 07 (Nicolas Lidzborski, Google).
• Securing Your Agents: Agentic Dev Security — Source:…
• Claude Code on the DFIR SIFT Workstation — A practitioner talk by Rob T.
• Securing the Software Supply Chain with AI (Snyk) — Source: Snyk — How to Secure the Software Supply Chain with AI (undated ever…
• STRIDE-AI Threat Modeling Framework — Academic proposal (arXiv:2605.17163, CIIT 2026; Tsafac Nkombong Regine Cyrille, Franziska Schwarz) th…
• SYARA: Semantic Rules for GenAI Threats — Source: SYARA on GitHub · syara.org ·…
• Taming Shai-Hulud with AI — A practitioner post-mortem by Rami McCarthy (Wiz) at Unprompted (March 2026) on responding to the 2025 Shai-Hulud campaigns.
• Trajectory-Aware Post-Training for Security Agents — A practitioner talk by Aaron Brown (with Madhur Prashant, AWS) at the March 2026 Unprompted Conference.
• Unprompted Conference I — Source: unpromptedcon.org agenda; talk videos on the @un_prompted YouTube channel.
• Verizon DBIR 2026 — Source: Verizon Business, 2026 Data Breach Investigations Report (19th edition), local copy .raw/papers/verizon-dbir-2026.pdf.
• Trends in Vulnerability Exploitation — VulnCheck’s quarterly exploitation-trends report (Patrick Garrity) draws on its own tracking of vulnerabilities first observed exploited…
• From Threat Intel to VulnOps — Source:…
• Non-Human Identities — Source: Oasis Security — What Are Non-Human Identities? (2026).
• Mythos for Offensive Security — Source: XBOW Blog — Mythos for Offensive Security: XBOW’s Evaluation (…
• your-agent-works-for-me-now-talk — Source: Transcript via attendee Google Drive share (conference-…