Prompt injection attacks can self-replicate across LLM agents in multi-agent systems, enabling data theft, misinformation, and system disruption while propagating silently.
ToolSword : Unveiling Safety Issues of Large Language Models in Tool Learning Across Three Stages , August 2024
3 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
3
Pith papers citing it
2
external citations · external index
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
MCP lifecycle is defined with four phases and 16 activities; a threat taxonomy of 16 scenarios is constructed, validated via case studies, and paired with phase-specific safeguards.
Standard observables fail to support delegation-scoped attribution in agentic AI systems, requiring a new gateway and common information model to bind context at execution time.
citing papers explorer
-
Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems
Prompt injection attacks can self-replicate across LLM agents in multi-agent systems, enabling data theft, misinformation, and system disruption while propagating silently.
-
Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions
MCP lifecycle is defined with four phases and 16 activities; a threat taxonomy of 16 scenarios is constructed, validated via case studies, and paired with phase-specific safeguards.
-
Observability for Delegated Execution in Agentic AI Systems
Standard observables fail to support delegation-scoped attribution in agentic AI systems, requiring a new gateway and common information model to bind context at execution time.