No major agentic AI framework complies with six safety containment principles; a memory poisoning attack on LangChain causes persistent targeted errors up to 88.9% wrongful denials and 3.5x increase under complex policies, fixed by two sub-millisecond validators.
Real ai agents with fake memories: Fatal context manipulation attacks on web3 agents
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 2representative citing papers
The paper defines and evaluates Trojan Hippo attacks on LLM agent memory, showing 85-100% success in data exfiltration across backends and reduced rates with defenses at varying utility costs.
ElephantAgent maintains a linearizable ledger of contextual state transitions via replicated trusted hardware and adds historical traceability for post-hoc recovery from semantic abuse in agentic systems.
The paper systematizes security for LLM agents in agentic commerce into five threat dimensions, identifies 12 cross-layer attack vectors, and proposes a layered defense architecture.
A synthesis of 247 papers on LLM agent security identifies prompt injection and tool hijacking as dominant threats, notes weakly compositional defenses, and argues for trust boundaries and realistic evaluations.
citing papers explorer
-
Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration
The paper defines and evaluates Trojan Hippo attacks on LLM agent memory, showing 85-100% success in data exfiltration across backends and reduced rates with defenses at varying utility costs.
-
SoK: Security of Autonomous LLM Agents in Agentic Commerce
The paper systematizes security for LLM agents in agentic commerce into five threat dimensions, identifies 12 cross-layer attack vectors, and proposes a layered defense architecture.
-
Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation
A synthesis of 247 papers on LLM agent security identifies prompt injection and tool hijacking as dominant threats, notes weakly compositional defenses, and argues for trust boundaries and realistic evaluations.