A Comparative Evaluation of AI Agent Security Guardrails

Computer Science > Cryptography and Security [Submitted on 27 Apr 2026] A Comparative Evaluation of AI Agent Security Guardrails Qi Li, Jiu Li, Pingtao Wei, Jianjun Xu, Xueyi Wei, Jiwei Shi, Xuan Zhang, Yanhui Yang, Xiaodong Hui, Peng Xu, Lingquan Zhou This report presents a comparative evaluation of DKnownAI Guard in AI agent security scenarios, benchmarked against three competing products: AWS Bedrock Guardrails, Azure Content Safety, and Lakera Guard. Using human annotation as the ground truth, we assess each guardrail's ability to detect two categories of risks: threats to the agent itself (e.g., instruction override, indirect injection, tool abuse) and requests intended to elicit harmful content (e.g., hate speech, pornography, violence). Evaluation results demonstrate that DKnownAI Guard achieves the highest recall rate at 96.5\% and ranks first in true negative rate (TNR) at 90.4\%, delivering the best overall performance among all evaluated guardrails. Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) Cite as: arXiv:2604.24826 [cs.CR]   (or arXiv:2604.24826v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2604.24826 Focus to learn more Submission history From: Qi Li [view email] [v1] Mon, 27 Apr 2026 15:44:32 UTC (26 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)