AI Threat Alert
Benchmark MEDIUM relevance
Blue Teaming Function-Calling Agents
Greta Dolcetti Giulio Zizzo Sergio Maffeis
Abstract
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.
Metadata
- Comment
- This work has been accepted to appear at the AAAI 2026 Workshop on Trust and Control in Agentic AI (TrustAgent)
Pro Analysis
Full threat analysis, ATLAS technique mapping, compliance impact assessment (ISO 42001, EU AI Act), and actionable recommendations are available with a Pro subscription.
Threat Deep-Dive
ATLAS Mapping
Compliance Reports
Actionable Recommendations