{"data":{"id":"f24cf972-a3e5-48c5-9652-e6eb122b6f0f","title":"New MemGhost Attack Plants Persistent False Memories in AI Agents Through One Email","summary":"Researchers discovered MemGhost, an attack that tricks AI agents (assistants that remember information about you across sessions) into secretly storing false information through a single specially crafted email. The planted false \"memory\" then influences the agent's future responses without the user noticing, because the agent hides its file-editing steps and users rarely check raw memory files. The attack succeeded in 87.5% of background-mode tests, showing that agents reading email inboxes are vulnerable to having their persistent memories poisoned.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://thehackernews.com/2026/07/new-memghost-attack-plants-persistent.html","publishedAt":"2026-07-13T13:49:48.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["rag_poisoning","prompt_injection"],"issueType":"news","affectedPackages":null,"affectedVendors":["OpenAI"],"affectedVendorsRaw":["OpenAI","OpenClaw","Anthropic Claude","GPT-5.4","Claude Code SDK","Sonnet 4.6"],"classifierModel":"claude-haiku-4-5-20251001","classifierPromptVersion":"v3","cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"patchAvailable":null,"disclosureDate":"2026-07-13T13:49:48.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","confidentiality"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.92,"researchCategory":null,"atlasIds":null}}