★ NO REAL MONEY ★ INTEL: GitHub roadmap: Immutable Actions Publishing for GitHub Actions ◆ Will a jailbreak prompt sell as an NFT for more than 1 ETH before 2027 — NO 95.0% ◆ Will itspricedin.lol itself get pwned within 90 days of launch? — YES 99.1% ◆ Will a prompt injection attack be publicly blamed for a data breach at — YES 62.0% ◆ Will an executive literally say 'it's priced in' about a breach on an — NO 85.0% ◆ INTEL: Shockwave - attack surface and continuous threat exposure management platform ◆ Will $POC ever be worth anything? — NO 99.9% ◆ Which AI lab discloses the next headline security incident? — OpenAI 46.2% ◆ Will a CVSS 9.0+ RCE be disclosed in a major AI coding agent before 20 — YES 80.5% ◆ INTEL: PromptQL - Confidently Wrong ◆ Will an AI browser agent be shown exfiltrating user data via prompt in — YES 70.0% ◆ INTEL: How to build an offensive AI security agent ◆ INTEL: Burp2API - convert Burp Suite projects into JSON APIs ◆ INTEL: OWASP AI Agent Security Cheat Sheet ◆ Will a leaked system prompt lead to a public apology from a major AI l — NO 70.0% ◆ INTEL: Semantic Attacks on Tool-Augmented LLMs: Securing the Model Context Protocol Aga ◆ Will AI-generated bug reports cause a major open-source project to shu — YES 55.0% ◆ Will a global Cloudflare, AWS, or Azure outage lasting over 3 hours be — YES 55.0% ◆ INTEL: Leaked Secrets and Unlimited Miles: Hacking the Largest Airline and Hotel Reward ◆ Will a major password manager disclose a CVSS 9.0+ vulnerability befor — NO 60.0% ◆ ★ $POC HAS NO VALUE ★ ◆
🕵️ Intel feed — 5660 resources from the ai-security compendium
Clear

Categories: Agent Frameworks · Agent Identity · Agent Security · Anti-Crawling · Architecture · Benchmarks · Code Analysis · Coding Tools · Detection and Monitoring · Engineering Patterns · Frameworks and Standards · General Reading · Governance and Policy · Guardrails and Firewalls · Honeypots and Deception · Incidents · Jailbreaking · MCP (Model Context Protocol) · Model Attacks · Papers · Privacy · Prompt Injection · Red Teaming · Safety and Alignment · Sandboxing and Isolation · Secrets Management · Secure Coding · Supply Chain · Threat Modeling

Showing 31 of 31. Source: github.com/AnthonyHerman/ai-security-corpus · browse it in Internet Explorer. This is the research; the markets are the bets.

Snapshot 2026-10-10 · last checked 2026-10-13 14:25 UTC · NEW = added in the last 14 days (nothing fresh this fortnight; the bugs are resting)

TitleCategorySection
NCC Group - Analyzing Secure AI ArchitecturesArchitectureDesign Principles and Patterns
Microsoft - Best Practices to Architect Secure GenAI ApplicationsArchitectureDesign Principles and Patterns
NCC Group - Analyzing Secure AI Design PrinciplesArchitectureDesign Principles and Patterns
Simon Willison - Dual LLM PatternArchitectureDesign Principles and Patterns
Simon Willison - CAMELArchitectureDesign Principles and Patterns
awesome-secure-defaults - secure-by-default libraries that eliminate bug classesArchitectureDesign Principles and Patterns
Beyond Zero: Enterprise security for the AI eraArchitectureDesign Principles and Patterns
Designing Patterns to Prevent IDORArchitectureDesign Principles and Patterns
Misty Programming Language: Security - capability discipline and the policy machineArchitectureDesign Principles and Patterns
Shifting the Balance of Cybersecurity Risk - Principles and Approaches for Security-by-Design and -DefaultArchitectureDesign Principles and Patterns
Tackling cybersecurity vulnerabilities through Secure by Design - GoogleArchitectureDesign Principles and Patterns
The Rule Of 2 - Chromium's security rule for handling untrustworthy inputsArchitectureDesign Principles and Patterns
Agent-native Architectures: How to Build Apps After Code EndsArchitectureAI System Architectures
fleetwood.devArchitectureAI System Architectures
SPQA: The AI-based Architecture That'll Replace Most Existing SoftwareArchitectureAI System Architectures
CrowdStrike and NVIDIA Unveil Secure-by-Design AI Blueprint for AI AgentsArchitectureAI System Architectures
Data Poisoning Vulnerabilities Across Healthcare AI Architectures: A Security Threat AnalysisModel AttacksData Poisoning
XBOW on how its autonomous offensive security agent architecture prevents OpenAI-Hugging Face style incidentsAgent SecurityAgent Security Frameworks and Tools
Scaling MCP adoption: Cloudflare's reference architecture for safer enterprise MCP deploymentsMCP (Model Context Protocol)General Reading
AGENTS.md gist - ADR docs plus a record-architecture-decisions agent skillAgent FrameworksAgent Engineering
May I have your Attention? Breaking Fine-Tuning based Prompt Injection Defenses using Architecture-Aware AttacksPapersPrompt Injection and Jailbreaking
ACE: A Security Architecture for LLM-Integrated App SystemsPapersAgent Security
Fortifying the Agentic Web: A Unified Zero-Trust Architecture Against Logic-layer ThreatsPapersAgent Security
Baselines Before Architecture: Evaluating Coding Agents for Autonomous Penetration TestingPapersOffensive Security and Red Teaming
Can AI Keep a Secret? Contextual Integrity Verification: A Provable Security Architecture for LLMsPapersDefense and Detection
Inside the Benchmark: App Architectures, Finding Walkthroughs, and What Each Scanner Actually CaughtBenchmarksSecurity and Risk Benchmarks
Agentic Context Management: Solving Agent Memory and Cost as Lifecycle and Architecture ProblemsEngineering PatternsHarness Engineering
improve-codebase-architecture - mattpocock Claude Code skillEngineering PatternsHarness Engineering
OpenMythos - theoretical reconstruction of the Claude Mythos architectureGeneral ReadingAI Industry and Ecosystem
Agentic AI Mesh Architecture (McKinsey)General ReadingAI Engineering
OpenSecurityTraining2 - free courses on x86 architecture, reverse engineering and debuggingGeneral ReadingTutorials and Learning
Remember: every breach is priced in. Except the ones that aren't.
📎
💰 get $POC --:--