Skip to content
InfoResearchPreprintLLM-specific

ACaM: Automated Capability Modeling for Agentic AI Security

Published
Record updated
View JSON

Summary

ACaM is a neurosymbolic capability-modeling approach for agentic AI that derives each tool's capabilities from its code rather than its natural-language description, targeting Description-Code Inconsistency and capability laundering. It compiles agent source code into an Agent Capability Property Graph to reconstruct multi-tool threat chains. Evaluated on 43 real-world agents, it reached 98.3% macro-F1 on 24 annotated agents and discovered hundreds of structural vulnerabilities, ten confirmed with proof-of-concept exploits.