{"schemaVersion":1,"target":{"type":"reading","id":"e253d82ad0eadcb545b02e72f48742034c239f91730ac7827f1141f96a222f55","revision":"fa92c944-b94c-4de8-8c08-8819cde7cbbb","revisionKind":"publication-id","title":"arXiv cs.AI paper reports that agent self-evolution can weaken defenses against indirect prompt injection","url":"https://escapemeridian.com/readings/arxiv-cs-ai-paper-reports-that-agent-self-evolution-can-weaken-e253d82a"},"source":{"type":"source","id":"https://arxiv.org/abs/2610.39122","revision":"9e3bd0c2e42a75ad237791e221b82a1a0bf4cfd31d7ac7f1870786790cb9f4da","revisionKind":"sha256-source-text","title":"Appreciation Teaches Unauthorized Execution: Self-Evolution Degrades the Robustness of Personal Agents to Indirect Prompt Injection","url":"https://arxiv.org/abs/2610.39122"},"status":"available","items":[],"next":null,"scope":"Explicit citations in public readings and public file attachments to this reading. Shared topics are not citations. Other artifact types need an explicit reference adapter."}