# A Comparative Evaluation of AI Agent Security Guardrails

Source: [A Comparative Evaluation of AI Agent Security Guardrails](<https://www.sota2.com/research/paper/69f1906955a3c32af89fb90b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-30T05:00:04.704Z

Authors: Qi Li, Jiu Li, Pingtao Wei, Jianjun Xu, Xueyi Wei, Jiwei Shi, Xuan Zhang, Yanhui Yang, Xiaodong Hui, Peng Xu, Lingquan Zhou

Published: 2026-04-27T15:44:32.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Security Guardrail Detection on Security Guardrail Evaluation Dataset (Mixed)](<https://www.sota2.com/research/sota/security-guardrail-detection-on-security-guardrail-evaluation-dataset-mixed.md>): Security Guardrail Detection; Security Guardrail Evaluation Dataset (Mixed); Recall: 822.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.24826>)

[PDF](<https://arxiv.org/pdf/2604.24826.pdf>)
