Source record

Published by arXiv cs.MA (T1 source). The original is at https://arxiv.org/abs/2607.14611.

Pipeline notes

The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.

The paper evaluates prompt injection attacks via persistent memory in agentic systems, testing Claude Code and OpenAI Codex across four models. Planted payloads in memory files successfully attack current and future sessions, though success varies by system, model, and attack sequence.

Empirical study quantifying how persistent memory in Claude Code and Codex enables cross-session prompt injection, with measured attack success across four frontier models.

Cited by

• Safe models do not compose into safe systems