Blue Teaming Function-Calling Agents
On the map: LLM agents and tool use → Agent threats, guardrails and governance
Abstract (arXiv)
We present an experimental evaluation that assesses the robustness of four open source LLMs claiming function-calling capabilities against three different attacks, and we measure the effectiveness of eight different defences. Our results show how these models are not safe by default, and how the defences are not yet employable in real-world scenarios.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 4 of its 8 references that are in the map. First posted on arXiv 14 Jan 2026.
Builds on
4 of 8 references.
Closest ancestors · 3
Same direction, newest first
- 2025DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents13 Jun
- 2024From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection13 Dec
- 2024Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents3 Oct
Other references · 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Adaptive Evaluation of Out-of-Band Defenses Against Prompt Injection in LLM Agents
- 2024AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
- 2025SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning
- 2025Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks
- 2025A Survey on Agentic Security: Applications, Threats and Defenses
- 2026Early Detection of Distributed Backdoors in Multi-Agent LLM Systems: A Characterization Study
- 2026SoK: When Safe Agents Fail Together: The Security of Multi Agent LLM Systems
- 2025On the Robustness of Agentic Function Calling