AI Recommendation Poisoning: How "Ask AI" Buttons Silently Alter LLM Memory

A new class of prompt injection is spreading across commercial websites. It requires no malware, no stolen credentials, and no zero-day exploit. It abuses a standard feature built into almost every major AI assistant: pre-filled deep links. We observed production websites embedding hidden prompt...

Masking Vulnerability Scan reports

Continuing the series of posts about Kenna "Analyzing Vulnerability Scan data", "Connectors and REST API" and similar services. Is it actually safe to send your vulnerability data to some external cloud service for analysis? Leakage of such information can potentially cause great damage to your...