Prompt Infection: research paper

Research question

Can a prompt injection spread between agents in a multi-agent system?

Key findings

Self-replicating prompts propagate through agent communication channels - Attacks succeed in data theft, scam and system-wide disruption scenarios; tagging agent messages reduces spread

Sources

arxiv.orghttps://arxiv.org/abs/2410.07283

Contribute

Spot an error, or know a record we should add? Members can propose additions and submit corrections.

Submit research Report a correction or request removal

Related in Research Paper Library

Detecting Logic Vulnerabilities Across the Contract and Device Layers of Blockchain-Enabled IoT With Multi-Agent Heterogeneous Graph Attention

Blockchain-enabled Internet of Things (IoT) systems integrate smart contracts with embedded devices to support decentralized device management and access control. Their security therefore depends jointly on the logic…

Multi-agent security2026

MAGS: Multi-agent Auto-formalization Guarantees Safety for Agentic Outputs

LLM coding agents now generate complex programs at a scale that makes thorough human review increasingly difficult, raising the risk of safety and security failures. Common approaches, including fuzz testing, static…

Multi-agent security2026

Trust propagation and structural containment in Multi-agent LLM pipelines

Multi-agent LLM systems increasingly automate tasks involving agents with different levels of privilege, creating a security risk in which a compromised low-privilege agent can influence a higher-privilege agent and…

Multi-agent security2026