Agent Skills has structural security weaknesses from missing data-instruction boundaries, single-approval persistent trust, and absent marketplace reviews that require fundamental redesign.
hub Canonical reference
Navigating the risks: A survey of security, privacy, and ethics threats in llm-based agents
Canonical reference. 83% of citing Pith papers cite this work as background.
15
Pith papers citing it
8
external citations · external index
Background
83% of classified citations
hub tools
citation-role summary
background 5
baseline 1
citation-polarity summary
representative 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.
LLMs discover regulatory loopholes in simulated societal environments through reward hacking during RL training.
Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.
MCP-BiFlow detects 93.8% of known bidirectional data-flow vulnerabilities in MCP servers and identifies 118 confirmed issues across 87 real-world servers from a scan of 15,452 repositories.
A multi-level taxonomy of risks, attacks, and defenses across the full embodied AI pipeline, synthesizing 500+ papers and flagging overlooked failure modes.
BlindGuard introduces an unsupervised hierarchical agent encoder plus corruption-guided contrastive detector that identifies malicious agents in LLM-based multi-agent systems without any attack labels or prior knowledge of malicious behaviors.
A data-centric survey finds that only information-flow control covers compositional and cross-session leakage in LLM agents and that no single benchmark tests an agent across all its data surfaces under one policy.
Interviews with 20 practitioners show MCP supports cross-system collaboration and task decoupling in LLM workflows but is limited by ecosystem fragmentation, coordination issues, and state management problems.
A three-layer probabilistic assume-guarantee architecture is structurally required for safe LLM agent deployment.
ParDef defends DNNs against sparse, continuous, and structured parameter attacks via keyed reparameterization, error-correcting quantization, and robust inference, with evaluations on CIFAR and Tiny-ImageNet showing reduced attack success and maintained accuracy.
Privacy attacks on LLMs show strong signals for membership inference and backdoors but weaker performance for attribute inference and data extraction, with risks highly dependent on system configuration.
LARA-HPC introduces a validation-first agentic system with dry-run verification and multi-phase refinement that improves robustness of AI-generated DFT workflows on HPC systems.
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 deconstructs LLM agent systems via a methodology-centered taxonomy linking design principles to emergent behaviors, applications, and challenges.
citing papers explorer
-
Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security Analysis
Agent Skills has structural security weaknesses from missing data-instruction boundaries, single-approval persistent trust, and absent marketplace reviews that require fundamental redesign.
-
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.
-
Large Language Models Hack Rewards, and Society
LLMs discover regulatory loopholes in simulated societal environments through reward hacking during RL training.
-
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
Memory-equipped LLM agents exhibit increasing safety violation rates as memory accumulates across independent tasks, termed temporal memory contamination, detected via a new trigger-probe protocol.
-
Unsafe by Flow: Uncovering Bidirectional Data-Flow Risks in MCP Ecosystem
MCP-BiFlow detects 93.8% of known bidirectional data-flow vulnerabilities in MCP servers and identifies 118 confirmed issues across 87 real-world servers from a scan of 15,452 repositories.
-
Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
A multi-level taxonomy of risks, attacks, and defenses across the full embodied AI pipeline, synthesizing 500+ papers and flagging overlooked failure modes.
-
BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks
BlindGuard introduces an unsupervised hierarchical agent encoder plus corruption-guided contrastive detector that identifies malicious agents in LLM-based multi-agent systems without any attack labels or prior knowledge of malicious behaviors.
-
Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents
A data-centric survey finds that only information-flow control covers compositional and cross-session leakage in LLM agents and that no single benchmark tests an agent across all its data surfaces under one policy.
-
Understanding How Enterprises Adopt the Model Context Protocol for LLM-Driven Software Engineering
Interviews with 20 practitioners show MCP supports cross-system collaboration and task decoupling in LLM workflows but is limited by ecosystem fragmentation, coordination issues, and state management problems.
-
Position: A Three-Layer Probabilistic Assume-Guarantee Architecture Is Structurally Required for Safe LLM Agent Deployment
A three-layer probabilistic assume-guarantee architecture is structurally required for safe LLM agent deployment.
-
Toward a Generalized Defense Across Sparse, Continuous, and Structured Parameter Attacks
ParDef defends DNNs against sparse, continuous, and structured parameter attacks via keyed reparameterization, error-correcting quantization, and robust inference, with evaluations on CIFAR and Tiny-ImageNet showing reduced attack success and maintained accuracy.
-
On the Privacy of LLMs: An Ablation Study
Privacy attacks on LLMs show strong signals for membership inference and backdoors but weaker performance for attribute inference and data extraction, with risks highly dependent on system configuration.
-
LARA: Validation-Driven Agentic Supercomputer Workflows for Atomistic Modeling
LARA-HPC introduces a validation-first agentic system with dry-run verification and multi-phase refinement that improves robustness of AI-generated DFT workflows on HPC systems.
-
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.
-
Large Language Model Agent: A Survey on Methodology, Applications and Challenges
A survey that deconstructs LLM agent systems via a methodology-centered taxonomy linking design principles to emergent behaviors, applications, and challenges.