Skip to content
← Back to explorer

SafeSearch: Automated Red-Teaming of LLM-Based Search Agents

Jianshuo Dong, Sheng Guo, Hao Wang, Xun Chen, Zhuotao Liu, Tianwei Zhang, Ke Xu, Minlie Huang, Han Qiu · Sep 28, 2025 · Citations: 0

Automatic Metrics General Red Team
Open arXiv Find Implementation RSS feed Shortlist (0)

How to use this page

Moderate trust

Use this for comparison and orientation, not as your only source.

Best use

Secondary protocol comparison source

What to verify

Validate the evaluation procedure and quality controls in the full paper before operational use.

Evidence quality

Moderate

Derived from extracted protocol signals and abstract evidence.

Abstract

Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information. However, this also introduces a new threat surface: unreliable search results can mislead agents into producing unsafe outputs. Real-world incidents and our two in-the-wild observations show that such failures can occur in practice. To study this threat systematically, we propose SafeSearch, an automated red-teaming framework that is scalable, cost-efficient, and lightweight, enabling sandboxed safety evaluation of search agents. Using this, we generate 300 test cases spanning five risk categories (e.g., misinformation and prompt injection) and evaluate three search agent scaffolds across 17 representative LLMs. Our results reveal substantial vulnerabilities in LLM-based search agents, with the highest ASR reaching 90.5% for GPT-4.1-mini in a search-workflow setting. Moreover, we find that common defenses, such as reminder prompting, offer limited protection. Overall, SafeSearch provides a practical way to measure and improve the safety of LLM-based search agents.

Should You Rely On This Paper?

This paper has useful evaluation signal, but protocol completeness is partial; pair it with related papers before deciding implementation strategy.

Best use

Secondary protocol comparison source

Use if you need

A secondary eval reference to pair with stronger protocol papers.

Main weakness

No major weakness surfaced.

Trust level

Moderate

Usefulness score

65/100 • Medium

Useful as a secondary reference; validate protocol details against neighboring papers.

Human Feedback Signal

Detected

Evaluation Signal

Detected

Usefulness for eval research

Moderate-confidence candidate

Extraction confidence 70%

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

What We Could Verify

These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.

Human Feedback Types

strong

Red Team

Directly usable for protocol triage.

"Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information."

Evaluation Modes

strong

Automatic Metrics

Includes extracted eval setup.

"Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information."

Quality Controls

missing

Not reported

No explicit QC controls found.

"Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information."

Benchmarks / Datasets

missing

Not extracted

No benchmark anchors detected.

"Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information."

Reported Metrics

strong

Jailbreak success rate

Useful for evaluation criteria comparison.

"Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information."

Human Feedback Details

  • Uses human feedback: Yes
  • Feedback types: Red Team
  • Rater population: Not reported
  • Expertise required: General

Evaluation Details

  • Evaluation modes: Automatic Metrics
  • Agentic eval: None
  • Quality controls: Not reported
  • Evidence quality: Moderate
  • Use this page as: Secondary protocol comparison source

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

jailbreak success rate

Research Brief

Metadata summary

Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information.

Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.

Key Takeaways

  • Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information.
  • However, this also introduces a new threat surface: unreliable search results can mislead agents into producing unsafe outputs.
  • Real-world incidents and our two in-the-wild observations show that such failures can occur in practice.

Researcher Actions

  • Compare this paper against nearby papers in the same arXiv category before using it for protocol decisions.
  • Check the full text for explicit evaluation design choices (raters, protocol, and metrics).
  • Use related-paper links to find stronger protocol-specific references.

Caveats

  • Generated from abstract + metadata only; no PDF parsing.
  • Signals below are heuristic and may miss details reported outside the abstract.

Recommended Queries

Research Summary

Contribution Summary

  • Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date information.
  • To study this threat systematically, we propose SafeSearch, an automated red-teaming framework that is scalable, cost-efficient, and lightweight, enabling sandboxed safety evaluation of search agents.
  • Our results reveal substantial vulnerabilities in LLM-based search agents, with the highest ASR reaching 90.5% for GPT-4.1-mini in a search-workflow setting.

Why It Matters For Eval

  • To study this threat systematically, we propose SafeSearch, an automated red-teaming framework that is scalable, cost-efficient, and lightweight, enabling sandboxed safety evaluation of search agents.
  • Our results reveal substantial vulnerabilities in LLM-based search agents, with the highest ASR reaching 90.5% for GPT-4.1-mini in a search-workflow setting.

Researcher Checklist

  • Pass: Human feedback protocol is explicit

    Detected: Red Team

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Pass: Metric reporting is present

    Detected: jailbreak success rate

Related Papers

Papers are ranked by protocol overlap, extraction signal alignment, and semantic proximity.

Get Started

Join the #1 Platform for AI Training Talent

Where top AI builders and expert AI Trainers connect to build the future of AI.
Self-Service
Post a Job
Post your project and get a shortlist of qualified AI Trainers and Data Labelers. Hire and manage your team in the tools you already use.
Create Account & Post a Job
Managed Service
For Large Projects
Done-for-You
We recruit, onboard, and manage a dedicated team inside your tools. End-to-end operations for large or complex projects.
Learn About Managed Service
For Freelancers
Join as an AI Trainer
Find AI training and data labeling projects across platforms, all in one place. One profile, one application process, more opportunities.
Join Now