Presents TRUST-Bench benchmark for hidden-trigger tool compromises in LLM agents and VISTA-Guard framework for trajectory-aware risk scoring of final actions under untrusted feedback.
Agentsys: Secure and dynamic llm agents through explicit hierarchical memory management
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 7verdicts
UNVERDICTED 7roles
background 1polarities
background 1representative citing papers
Formalizes stored prompt injection in agentic systems, develops a taxonomy and benchmark to show how adversarial prompts can persist across sessions via persistent state artifacts.
In LLM agents, memory routing circuits emerge at 0.6B scale while content circuits appear only at 4B, and write/read operations recruit a pre-existing late-layer context hub instead of creating a new one, enabling a 76% accurate unsupervised failure diagnostic.
Protected policy placements in LLM agents maintain integrity under replay pressure on AutoGen and OpenHands traces, unlike task-local placements which show eviction or weakening.
SafeAgent is a stateful runtime protection system that improves LLM agent robustness to prompt injections over baselines while preserving task performance.
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.
A survey that categorizes threats to OpenClaw agents including skill poisoning and cognitive manipulation and reviews defense mechanisms.
citing papers explorer
-
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.