The security intelligence platform for AI teams
AI security threats move fast and get buried under hype and noise. Built by an Information Systems Security researcher to help security teams and developers stay ahead of vulnerabilities, privacy incidents, safety research, and policy developments.
Independent research. No sponsors, no paywalls, no conflicts of interest.
Flowise AI Platform Suffers Multiple Critical RCEs: Flowise versions before 3.1.3 contain two critical vulnerabilities allowing unauthenticated attackers to execute arbitrary Python code through prompt injection (tricking the AI by hiding instructions in input) in CSV and Airtable Agent nodes, bypassing weak regex-based validators to gain full host system access in an unsandboxed environment. (CVE-2026-73487, CVE-2026-73485)
vLLM Inference Engine Hit by Wave of Security Flaws: vLLM, a widely-used large language model serving engine, disclosed multiple vulnerabilities in versions before 0.26.0 including concurrent request race conditions that bypass prompt embedding safety checks, information disclosure through error messages, regex-based denial of service attacks, and an integer overflow bug that could leak one user's AI outputs to another. (CVE-2026-73557, CVE-2026-73555, CVE-2026-73556, CVE-2026-73558)
Microsoft Warns AI Is Transforming Attack Economics: Microsoft security leaders presented evidence that AI tools now generate working exploits for vulnerabilities in 21 minutes at $3.61 cost, making traditional reactive patching and defenses like ASLR (address space layout randomization, which makes system memory locations unpredictable) increasingly ineffective as vulnerability processing volume increases nine-fold.
Autonomous AI Agents Conduct Multi-Day Attack on Asian Government: Autonomous AI agents built on open-source frameworks executed a coordinated cyberattack on Asian government networks across 12 waves, creating thousands of fake accounts and stealing personnel records while using parallel AI systems to perform reconnaissance, crack credentials, and exploit vulnerabilities at dramatically reduced cost compared to traditional attacks.
Researchers suggest that AI safety could be improved by examining the internal workings of LLMs (large language models, AI systems trained on massive amounts of text data) to identify specific patterns that might signal when an AI system could perform an unwanted or harmful action. Rather than treating AI systems as mysterious black boxes, the researchers argue that looking inside these systems to understand how they think could help prevent problems.