#AI Security
JADEPUFFER shows how agentic AI can turn exposed Langflow into ransomware
JADEPUFFER shows how agentic AI can turn exposed Langflow into ransomware Sysdig has documented what it assesses as one of the first clear examples of agentic r...
Lucas Oliveira
Research
Mastra npm compromise turns AI agent builds into credential-theft risk
Mastra npm compromise turns AI agent builds into credential-theft risk The Mastra npm incident is a sharp warning for teams building AI agents: dependency compr...
Lucas Oliveira
Research
CVE-2026-45829: ChromaDB Pre-Auth RCE Risk in AI Stacks
CVE-2026-45829: ChromaDB Pre-Auth RCE Risk in AI Stacks | 2026 Executive Summary CVE-2026-45829 is a critical ChromaDB flaw that can let unauthenticated attacke...
Lucas Oliveira
Research
LiteLLM SQL injection flaw puts AI gateways on the front line
LiteLLM SQL injection flaw puts AI gateways on the front line CVE-2026-42208 matters because it turns an AI gateway into a high-value choke point for attackers....
Lucas Oliveira
Research
PyTorch Lightning supply-chain compromise puts AI developer credentials at risk
PyTorch Lightning supply-chain compromise puts AI developer credentials at risk The most dangerous supply-chain incidents are not always the ones that hit opera...
Lucas Oliveira
Research
CVE-2026-42208 turns exposed LiteLLM gateways into a secrets exposure risk
CVE-2026-42208 turns exposed LiteLLM gateways into a secrets exposure risk CVE-2026-42208 is a critical SQL injection flaw in LiteLLM's proxy API key verificati...
Lucas Oliveira
Research
Lovable Incident Raises Cross-Tenant Data Exposure Concerns for AI Development Platforms
Lovable Incident Raises Cross-Tenant Data Exposure Concerns for AI Development Platforms Lovable, an AI platform used to build and iterate software projects, is...
Lucas Oliveira
Research
CVE-2026-5752 turns the Terrarium sandbox into a root-level escape risk
CVE-2026-5752 turns the Terrarium sandbox into a root-level escape risk A critical flaw in Terrarium, tracked as CVE-2026-5752, deserves attention well beyond a...
Lucas Oliveira
Research
CVE-2026-33017: Langflow RCE Hits Exposed AI Pipelines
CVE-2026-33017: Langflow RCE Hits Exposed AI Pipelines | 2026 CVE-2026-33017 is a critical Langflow flaw that turns a public-flow convenience feature into unaut...
Lucas Oliveira
Research
Cline CLI 2.3.0 supply chain attack silently installed OpenClaw on developer systems
Cline CLI 2.3.0 supply chain attack silently installed OpenClaw on developer systems Executive summary The Cline CLI supply chain incident is a practical remind...
Lucas Oliveira
Research
Slopoly Shows How AI-Generated Malware Is Entering Ransomware Operations
Slopoly Shows How AI-Generated Malware Is Entering Ransomware Operations | 2026 Executive Summary IBM X-Force says a ransomware-linked intrusion involved a like...
Lucas Oliveira
Research