arXiv (OAI Expanded)
open access
When Malicious Instructions Persist: Persistent Memory Poisoning Attack on Harness-Based Agents
Harness design has transformed the development of LLM-based agents by integrating memory, tool use, and runtime control. However, this design also introduces security and privacy risks because malicious instructions from external sources may be written into persistent memory and persist across sessi
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- An Evaluation of Data Leakage Risks in Tool-Using LLM Agents in Realistic Scenarios#282741
- Insecure Coding Preferences in Long-Term Memory: Security Risks for LLM-based Code Generation#386774
- Runtime-Independent Persistent Agents: Preserving Identity, Memory, and Code Across Models, Harnesses, and Servers#627760
- ActionGuard: Tool Call Authorization under Poisoned Skills#1144417
- ActionGuard: Tool Call Authorization under Poisoned Skills#1136768
Record · ID 1083383
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive