A tool called m8m has launched to give users visibility into what AI agents remember about them, detecting memory poisoning and tracking memory provenance through a local SQLite database with an MCP s…
A security engineer built m8m, a tool for auditing the persistent memory files that AI coding agents like Claude Code, Codex, and Cursor write automatically, after finding no way to inspect what those…
A new attack called MemGhost achieves an 87.5% success rate against frontier AI models by exploiting persistent memory systems in AI agents. Instead of tricking the agent into a single action, MemGhos…
Researchers have developed WhisperBench, a benchmark of 108 test cases, and MemGhost, a framework that crafts one-shot email payloads, to demonstrate how persistent personal agents can be compromised …