When Malicious Instructions Persist: Persistent Memory Poisoning Attack on Harness-Based Agents

cs.CR, cs.AI

Submitted: 2026-09-12

Updated: 2026-09-12

Comments: 14 pages, 1 figures. Code: https://github.com/hsh754/PMPA

Code: https://github.com/hsh754/PMPA

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs