https://appsec.fyi/ai.html Curated AI Security resources from appsec.fyi en-us Sun, 12 Apr 2026 16:40:01 +0000 carl@chs.us (Carl Sampson) https://www.promptfoo.dev/docs/red-team/ https://www.promptfoo.dev/docs/red-team/ LLM Red Teaming Guide (Open Source) - Promptfoo AI Security Sat, 11 Apr 2026 16:40:13 +0000 https://developer.nvidia.com/blog/defining-llm-red-teaming/ https://developer.nvidia.com/blog/defining-llm-red-teaming/ Defining LLM Red Teaming - NVIDIA Technical Blog AI Security Sat, 11 Apr 2026 16:40:12 +0000 https://www.nature.com/articles/s41467-026-69010-1 https://www.nature.com/articles/s41467-026-69010-1 Large Reasoning Models are Autonomous Jailbreak Agents AI Security Sat, 11 Apr 2026 16:40:12 +0000 https://arxiv.org/abs/2508.13246 https://arxiv.org/abs/2508.13246 Involuntary Jailbreak: On Self-Prompting Attacks AI Security Sat, 11 Apr 2026 16:40:11 +0000 https://cyberpress.org/single-line-of-code-can-jailbreak-11-ai-models-including-chatgpt-claude-and-gemini/ https://cyberpress.org/single-line-of-code-can-jailbreak-11-ai-models-including-chatgpt-claude-and-gemini/ Single Line of Code Can Jailbreak 11 AI Models Including ChatGPT, Claude, Gemini AI Security Sat, 11 Apr 2026 16:40:10 +0000 https://www.invicti.com/blog/web-security/owasp-top-10-risks-llm-security-2025 https://www.invicti.com/blog/web-security/owasp-top-10-risks-llm-security-2025 OWASP Top 10 for LLMs 2025: Key Risks and Mitigation Strategies AI Security Sat, 11 Apr 2026 16:40:09 +0000 https://genai.owasp.org/resource/owasp-top-10-for-llm-applications-2025/ https://genai.owasp.org/resource/owasp-top-10-for-llm-applications-2025/ OWASP Top 10 for LLM Applications 2025 AI Security Sat, 11 Apr 2026 16:40:09 +0000 https://arxiv.org/abs/2504.03957 https://arxiv.org/abs/2504.03957 Practical Poisoning Attacks against Retrieval-Augmented Generation AI Security Sat, 11 Apr 2026 16:40:08 +0000 https://arxiv.org/abs/2507.08862 https://arxiv.org/abs/2507.08862 RAG Safety: Exploring Knowledge Poisoning Attacks to RAG AI Security Sat, 11 Apr 2026 16:40:07 +0000 https://arxiv.org/abs/2505.18543 https://arxiv.org/abs/2505.18543 Benchmarking Poisoning Attacks against Retrieval-Augmented Generation AI Security Sat, 11 Apr 2026 16:40:06 +0000 https://www.lakera.ai/ai-security-guides/q4-2025-ai-agent-security-trends https://www.lakera.ai/ai-security-guides/q4-2025-ai-agent-security-trends Q4 2025 AI Agent Security Trends AI Security Sat, 11 Apr 2026 16:40:06 +0000 https://genai.owasp.org/2025/12/09/owasp-genai-security-project-releases-top-10-risks-and-mitigations-for-agentic-ai-security/ https://genai.owasp.org/2025/12/09/owasp-genai-security-project-releases-top-10-risks-and-mitigations-for-agentic-ai-security/ OWASP GenAI Top 10 Risks and Mitigations for Agentic AI Security AI Security Sat, 11 Apr 2026 16:40:05 +0000 https://www.esecurityplanet.com/artificial-intelligence/ai-agent-attacks-in-q4-2025-signal-new-risks-for-2026/ https://www.esecurityplanet.com/artificial-intelligence/ai-agent-attacks-in-q4-2025-signal-new-risks-for-2026/ AI Agent Attacks in Q4 2025 Signal New Risks for 2026 AI Security Sat, 11 Apr 2026 16:40:04 +0000 https://developer.microsoft.com/blog/protecting-against-indirect-injection-attacks-mcp https://developer.microsoft.com/blog/protecting-against-indirect-injection-attacks-mcp Protecting Against Indirect Prompt Injection Attacks in MCP AI Security Sat, 11 Apr 2026 16:40:03 +0000 https://www.crowdstrike.com/en-us/blog/indirect-prompt-injection-attacks-hidden-ai-risks/ https://www.crowdstrike.com/en-us/blog/indirect-prompt-injection-attacks-hidden-ai-risks/ Indirect Prompt Injection Attacks: Hidden AI Risks AI Security Sat, 11 Apr 2026 16:40:03 +0000 https://unit42.paloaltonetworks.com/ai-agent-prompt-injection/ https://unit42.paloaltonetworks.com/ai-agent-prompt-injection/ Fooling AI Agents: Web-Based Indirect Prompt Injection Observed in the Wild AI Security Sat, 11 Apr 2026 16:40:02 +0000 https://www.pillar.security/blog/anatomy-of-an-indirect-prompt-injection https://www.pillar.security/blog/anatomy-of-an-indirect-prompt-injection Anatomy of an Indirect Prompt Injection AI Security Sat, 11 Apr 2026 16:40:01 +0000 https://jfrog.com/blog/2025-6514-critical-mcp-remote-rce-vulnerability/ https://jfrog.com/blog/2025-6514-critical-mcp-remote-rce-vulnerability/ Critical RCE Vulnerability in mcp-remote: CVE-2025-6514 AI Security Sat, 11 Apr 2026 16:40:00 +0000 https://unit42.paloaltonetworks.com/model-context-protocol-attack-vectors/ https://unit42.paloaltonetworks.com/model-context-protocol-attack-vectors/ New Prompt Injection Attack Vectors Through MCP Sampling AI Security Sat, 11 Apr 2026 16:40:00 +0000 https://authzed.com/blog/timeline-mcp-breaches https://authzed.com/blog/timeline-mcp-breaches A Timeline of Model Context Protocol (MCP) Security Breaches AI Security Sat, 11 Apr 2026 16:39:59 +0000 https://vulnerablemcp.info/ https://vulnerablemcp.info/ The Vulnerable MCP Project: Comprehensive MCP Security Database AI Security Sat, 11 Apr 2026 16:39:58 +0000 https://www.esentire.com/blog/model-context-protocol-security-critical-vulnerabilities-every-ciso-should-address-in-2025 https://www.esentire.com/blog/model-context-protocol-security-critical-vulnerabilities-every-ciso-should-address-in-2025 MCP Security: Critical Vulnerabilities Every CISO Must Address in 2025 AI Security Sat, 11 Apr 2026 16:39:57 +0000 https://cheatsheetseries.owasp.org/cheatsheets/LLM_Prompt_Injection_Prevention_Cheat_Sheet.html https://cheatsheetseries.owasp.org/cheatsheets/LLM_Prompt_Injection_Prevention_Cheat_Sheet.html OWASP LLM Prompt Injection Prevention Cheat Sheet AI Security Sat, 11 Apr 2026 16:39:56 +0000 https://aclanthology.org/2025.findings-naacl.123.pdf https://aclanthology.org/2025.findings-naacl.123.pdf Attention Tracker: Detecting Prompt Injection Attacks in LLMs AI Security Sat, 11 Apr 2026 16:39:56 +0000 https://www.microsoft.com/en-us/msrc/blog/2025/07/how-microsoft-defends-against-indirect-prompt-injection-attacks https://www.microsoft.com/en-us/msrc/blog/2025/07/how-microsoft-defends-against-indirect-prompt-injection-attacks How Microsoft Defends Against Indirect Prompt Injection Attacks AI Security Sat, 11 Apr 2026 16:39:55 +0000 https://www.practical-devsecops.com/mcp-security-vulnerabilities/ https://www.practical-devsecops.com/mcp-security-vulnerabilities/ MCP Security Vulnerabilities: Prompt Injection and Tool Poisoning AI Security Fri, 10 Apr 2026 01:52:17 +0000 https://www.crowdstrike.com/en-us/blog/how-agentic-tool-chain-attacks-threaten-ai-agent-security/ https://www.crowdstrike.com/en-us/blog/how-agentic-tool-chain-attacks-threaten-ai-agent-security/ How Agentic Tool Chain Attacks Threaten AI Agent Security AI Security Fri, 10 Apr 2026 01:52:17 +0000 https://cikce.medium.com/8-000-mcp-servers-exposed-the-agentic-ai-security-crisis-of-2026-e8cb45f09115 https://cikce.medium.com/8-000-mcp-servers-exposed-the-agentic-ai-security-crisis-of-2026-e8cb45f09115 8,000+ MCP Servers Exposed: The Agentic AI Security Crisis of 2026 AI Security Fri, 10 Apr 2026 01:52:16 +0000 https://www.penligent.ai/hackinglabs/agentic-ai-security-in-production-mcp-security-memory-poisoning-tool-misuse-and-the-new-execution-boundary/ https://www.penligent.ai/hackinglabs/agentic-ai-security-in-production-mcp-security-memory-poisoning-tool-misuse-and-the-new-execution-boundary/ Agentic AI Security in Production: MCP, Memory Poisoning, Tool Misuse AI Security Fri, 10 Apr 2026 01:52:15 +0000 https://equixly.com/blog/2026/02/26/offensive-security-for-mcp-servers/ https://equixly.com/blog/2026/02/26/offensive-security-for-mcp-servers/ Offensive Security for MCP Servers: How to Prevent AI Agent Exploits AI Security Fri, 10 Apr 2026 01:52:14 +0000 https://www.pillar.security/blog/the-new-ai-attack-surface-3-ai-security-predictions-for-2026 https://www.pillar.security/blog/the-new-ai-attack-surface-3-ai-security-predictions-for-2026 The New AI Attack Surface: 3 AI Security Predictions for 2026 AI Security Fri, 10 Apr 2026 01:52:14 +0000 https://www.lakera.ai/blog/training-data-poisoning https://www.lakera.ai/blog/training-data-poisoning Introduction to Data Poisoning: A 2026 Perspective AI Security Fri, 10 Apr 2026 01:52:13 +0000 https://medium.com/ai-security-hub/ai-security-research-december-2025-2955308744c2 https://medium.com/ai-security-hub/ai-security-research-december-2025-2955308744c2 AI Security Research — December 2025 AI Security Fri, 10 Apr 2026 01:52:12 +0000 https://www.sciencedirect.com/science/article/pii/S2405959525001997 https://www.sciencedirect.com/science/article/pii/S2405959525001997 From Prompt Injections to Protocol Exploits in LLM Agent Workflows AI Security Fri, 10 Apr 2026 01:52:11 +0000 https://github.com/requie/LLMSecurityGuide https://github.com/requie/LLMSecurityGuide LLM Security Guide: OWASP GenAI Top-10 Risks AI Security Fri, 10 Apr 2026 01:52:11 +0000 https://www.mdpi.com/2078-2489/17/1/54 https://www.mdpi.com/2078-2489/17/1/54 Prompt Injection Attacks in LLMs: A Comprehensive Review AI Security Fri, 10 Apr 2026 01:44:29 +0000 https://blog.cyberdesserts.com/prompt-injection-attacks/ https://blog.cyberdesserts.com/prompt-injection-attacks/ Prompt Injection Attacks: Examples, Techniques, and Defence AI Security Fri, 10 Apr 2026 01:44:29 +0000 https://www.lakera.ai/blog/indirect-prompt-injection https://www.lakera.ai/blog/indirect-prompt-injection Indirect Prompt Injection: The Hidden Threat AI Security Fri, 10 Apr 2026 01:44:28 +0000 https://swarmsignal.net/ai-agent-security-2026/ https://swarmsignal.net/ai-agent-security-2026/ AI Agent Security in 2026: Prompt Injection and Memory Poisoning AI Security Fri, 10 Apr 2026 01:44:27 +0000 https://blog.premai.io/prompt-injection-attacks-in-2025-vulnerabilities-exploits-and-how-to-defend/ https://blog.premai.io/prompt-injection-attacks-in-2025-vulnerabilities-exploits-and-how-to-defend/ Prompt Injection Attacks in 2025: Vulnerabilities and Defense AI Security Fri, 10 Apr 2026 01:44:26 +0000 https://www.obsidiansecurity.com/blog/prompt-injection https://www.obsidiansecurity.com/blog/prompt-injection Prompt Injection: The Most Common AI Exploit in 2025 AI Security Fri, 10 Apr 2026 01:44:26 +0000 https://theboard.world/articles/technology/ai-prompt-injection-attacks-how-they-work-2026/ https://theboard.world/articles/technology/ai-prompt-injection-attacks-how-they-work-2026/ AI Prompt Injection Attacks: How They Work (2026) AI Security Fri, 10 Apr 2026 01:44:25 +0000 https://sombrainc.com/blog/llm-security-risks-2026 https://sombrainc.com/blog/llm-security-risks-2026 LLM Security Risks in 2026: Prompt Injection, RAG, and Shadow AI AI Security Fri, 10 Apr 2026 01:44:24 +0000 https://repello.ai/blog/best-ai-security-tools https://repello.ai/blog/best-ai-security-tools Best AI Security Tools in 2026 AI Security Mon, 06 Apr 2026 02:04:17 +0000 https://unit42.paloaltonetworks.com/amazon-bedrock-multiagent-applications/ https://unit42.paloaltonetworks.com/amazon-bedrock-multiagent-applications/ Navigating Amazon Bedrock's Multi-Agent Applications AI Security Mon, 06 Apr 2026 02:04:16 +0000 https://trydeepteam.com/docs/frameworks-owasp-top-10-for-agentic-applications https://trydeepteam.com/docs/frameworks-owasp-top-10-for-agentic-applications OWASP Top 10 for Agents 2026 AI Security Mon, 06 Apr 2026 02:04:14 +0000 https://security.googleblog.com/2026/04/google-workspaces-continuous-approach.html https://security.googleblog.com/2026/04/google-workspaces-continuous-approach.html Google Workspace's Continuous Approach to Mitigating Prompt Injection AI Security Mon, 06 Apr 2026 02:04:13 +0000 https://www.securityjourney.com/post/prompt-injection-attacks-in-llms-what-developers-need-to-know-in-2026 https://www.securityjourney.com/post/prompt-injection-attacks-in-llms-what-developers-need-to-know-in-2026 Prompt Injection Attacks in LLMs: What Developers Need to Know in 2026 AI Security Mon, 06 Apr 2026 02:04:12 +0000 https://medium.com/@jannadikhemais/prompt-injection-attacks-in-large-language-models-vulnerabilities-exploitation-techniques-and-e00fe683f6d7 https://medium.com/@jannadikhemais/prompt-injection-attacks-in-large-language-models-vulnerabilities-exploitation-techniques-and-e00fe683f6d7 Prompt Injection Attacks in LLMs: Vulnerabilities, Exploitation & Defense AI Security Fri, 03 Apr 2026 15:59:29 +0000 https://invisibletech.ai/blog/ai-red-teaming-2026 https://invisibletech.ai/blog/ai-red-teaming-2026 How AI Red Teaming Fixes Vulnerabilities in Your AI Systems AI Security Fri, 03 Apr 2026 15:59:27 +0000