Topics
Browse everything AI Sec Weekly publishes by category and tag: every topic covered here, with the most recent guides listed under each one.
Tags
- #llm-security 13
- #prompt-injection 8
- #guardrails 6
- #agentic-ai 3
- #ai-red-teaming 3
- #ai-defense 2
- #ai-security 2
- #owasp-llm 2
- #owasp-llm-top-10 2
- #2026 1
- #agents 1
- #ai-agents 1
- #ai-attack-examples 1
- #ai-firewall 1
- #ai-gateway 1
- #ai-supply-chain 1
- #chatbots 1
- #csp 1
- #cve 1
- #data-exfiltration 1
- #detection-tools 1
- #jailbreak 1
- #jailbreaking 1
- #litellm 1
- #mcp-security 1
- #meta 1
- #mitre-atlas 1
- #model-supply-chain 1
- #nist-ai-rmf 1
- #offensive-ai 1
- #policy 1
- #rag 1
- #security-audit 1
- #sql-injection 1
- #supply-chain 1
- #supply-chain-security 1
- #threat-intel 1
- #threat-model 1
- #vulnerability-scanning 1
Categories
Threat Briefing 4 posts
- AI on Offense: Google's Zero-Day Warning and JailbreaksGoogle says it caught an attacker using an LLM to find a zero-day, and peer-reviewed work shows reasoning models can autonomously jailbreak other models.
- How LLM Chatbots Leak Data Through Their Own Rendered OutputA recurring AI-security finding: an injected instruction makes the model emit a markdown image whose URL carries the user's data to an attacker server.
- LiteLLM SQL Injection CVE-2026-42208: The AI Gateway RiskA pre-auth SQL injection in the LiteLLM proxy landed in CISA's KEV catalog and was exploited within roughly 36 hours of disclosure.
- Indirect Prompt Injection: The Agent Era's Default FlawAs LLM agents gained tools and memory, the dangerous injection stopped coming from the user and started coming from the data the agent reads.
Tooling 3 posts
- AI Security Scanning Tools for LLMs: 2026 Picks Comparedgarak, PyRIT and Promptfoo probe LLM behavior, ModelScan and picklescan check model files, and Snyk Agent Scan audits MCP servers.
- Best LLM Firewall Tools in 2026: A Buying GuideManaged APIs, in-process frameworks and open-weight classifiers compared: how to pick an LLM firewall architecture, and how to layer all three.
- Prompt Injection Detection Tools: The 2026 LandscapeA field guide to prompt injection detection tools: Llama Prompt Guard 2, Azure Prompt Shields, Lakera Guard, NeMo Guardrails, and the open-source options.
Attack Research 2 posts
- AI Agent Security Risks 2026: Injection to Privilege AbuseOWASP's Q1 2026 GenAI Exploit Round-up confirms AI agent security risks have moved from research to active production breaches.
- Prompt Injection Attack Examples: Direct, Indirect, AgenticA practitioner breakdown of prompt injection examples, from basic instruction overrides to CVE-rated zero-click exploits in production agent deployments.
Defense 2 posts
- LLM Prompt Injection Defense: What Actually WorksA layered guide to LLM prompt injection defense: prompt-level controls, classifier screening, agent design patterns, and the output gates that contain it.
- LLM Jailbreak Defense Techniques: A Practitioner's GuideA breakdown of LLM jailbreak defense techniques, from input filtering and model-level hardening to multi-agent architectures and OWASP mitigations.