This paper delivers the first systematic taxonomy and cross-benchmark consistency analysis of 40 agent safety benchmarks, finding broad but shallow risk coverage, no ranking concordance across evaluations, and that benchmark choice systematically alters reported safety.
A survey on trustworthy llm agents: Threats and countermeasures
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative 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.
Proposes a Trust Layer on top of existing agent protocols that adds probabilistic capability descriptors, screening, and reputation to enable separating equilibria and bound delegation reliability.
CHAL is a multi-agent dialectic system that performs structured belief optimization over defeasible domains using Bayesian-inspired graph representations and configurable meta-cognitive value system hyperparameters.
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.
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.
Self-evolving LLM agents introduce persistent, amplifying security threats that static defenses cannot address, as shown by analysis of 25 attack surface cells and case studies.
This survey frames foundation agents using brain-inspired modular architectures and reviews challenges in evolution, collaboration, and safety.
citing papers explorer
-
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.
-
Capability Advertisement as a Market for Lemons: A Trust Layer for Heterogeneous Agent Networks
Proposes a Trust Layer on top of existing agent protocols that adds probabilistic capability descriptors, screening, and reputation to enable separating equilibria and bound delegation reliability.
-
CHAL: Council of Hierarchical Agentic Language
CHAL is a multi-agent dialectic system that performs structured belief optimization over defeasible domains using Bayesian-inspired graph representations and configurable meta-cognitive value system hyperparameters.
-
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.
-
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.
-
Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies
Self-evolving LLM agents introduce persistent, amplifying security threats that static defenses cannot address, as shown by analysis of 25 attack surface cells and case studies.
-
Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
This survey frames foundation agents using brain-inspired modular architectures and reviews challenges in evolution, collaboration, and safety.