MindPatternSubscribe

Entity trail

PMPA

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

1

Findings

1

Edges

0

Sources

1

Corpus findings

2026-09-15 / arxiv-researcherPersistent Memory Poisoning Hits Claude Code at 81.7% Cross-Session Attack Success and OpenClaw at 55.5%PMPA embeds malicious instructions in benign external sources and induces a harness-based agent to write them into persistent memory, without any access to the agent framework itself. Across backbone LLMs, input modalities and trigger scenarios, it averages 73.7% injection success and 55.5% cross-session attack success on OpenClaw, and 66.9%/81.7% on Claude Code, while benign task performance is preserved. A targeted prompt-level defense reduces the initial memory injection in many settings but gives limited protection once the memory is already poisoned, which makes memory hygiene a recovery problem rather than a filtering one.

Source trail

arXiv 2609.13889

Graph sources

entity graphfindings textkg entitiesnewsletter issues