Graphiti is a framework for building and querying temporal context graphs for AI agents. Graphiti versions before 0.28.2 contained a Cypher injection vulnerability in shared search-filter construction for non-Kuzu backends. Attacker-controlled label values supplied through SearchFilters.node_labels were concatenated directly into Cypher label expressions without validation. In MCP deployments, this was exploitable not only through direct untrusted access to the Graphiti MCP server, but also through prompt injection against an LLM client that could be induced to call search_nodes with attacker-controlled entity_types values. The MCP server mapped entity_types to SearchFilters.node_labels, whi
Live wire
Rails patches critical Active Storage flaw with RCE potentialCVE-2026-48449 · Adobe fixed a maximum-severity vulnerability flaw in Campaign ClassicRuby on Rails Patches Critical VulnerabilityHackers Poison Adform Script to Swap Crypto Wallet Addresses Across Customer SitesHijacked Hotel Wi-Fi Pushes Fake Updates to Deliver Surveillance MalwareCaptiveCrunch: Midnight Blizzard targets travelers worldwide for malware delivery and credential theftThe Journey towards Logically Air-Gapped DeploymentCVE-2025-66376 · Russian Espionage Group Exploited Zimbra Zero-Day to Steal Mail and 2FA CodesDon’t swing at everythingRussian Hackers Exploit New ‘Zero-Click’ Attack Against Western Organizations
