Automating Attack Graph Construction for Agentic Pentesting. Towards Neuro-Symbolic Vulnerability Hunting
Semi-automated pipeline converts Trivy, Semgrep, Nmap output into MulVAL attack graphs for agentic pentesting, 53.7% mean vulnerability coverage in CyBench.
The paper presents a semi-automated pipeline that parses Trivy, Semgrep, and Nmap findings into MulVAL predicates and uses an LLM-assisted process to build domain-specific Datalog rules linking scanner evidence to attack techniques. MulVAL/XSB then performs symbolic inference to generate structured, auditable attack paths for agentic pentesting. Evaluated on 54 web CTF tasks from CyBench, every task produced at least one goal-reaching graph with 53.7% mean ground-truth vulnerability coverage, 51.9% full coverage, and an 83.9% noise-path rate. Median end-to-end runtime was 24.9 seconds, making the pipeline runtime-practical for agentic workflows.
- Translates Trivy, Semgrep, and Nmap findings into MulVAL predicates automatically
- LLM-assisted Datalog rules link scanner evidence to attack techniques
- All 54 CyBench CTF tasks yielded goal-reaching graphs; 53.7% mean coverage
- Median end-to-end runtime 24.9 s, feasible for agentic pentesting
Full article198 words · extracted from arxiv.org · click to collapse
Logic attack graphs grounded in scanner output provide explicit and auditable attack path reasoning LLM-based agents lack. Integrating symbolic frameworks such as MulVAL to contemporary security workflows or agentic pipelines, however, requires translating scanner evidence to initial facts, and creating domain-specific rules. We present a semi-automated pipeline that addresses this interoperability problem and depict its feasibility in a web-security case study. Our pipeline parses findings from Trivy, Semgrep, and Nmap into MulVAL predicates and uses an LLM-assisted process to construct domain-specific Datalog rules linking scanner-detectable evidence to attack techniques. MulVAL/XSB then performs symbolic inference to generate structured attack paths. We evaluate the attack-graph construction infrastructure on 54 web Capture-the-Flag tasks from CyBench within an agentic pipeline (Hybrid Reasoner); we do not evaluate the performance of the downstream agent. Every task produced at least one goal-reaching graph, and we achieve mean ground-truth vulnerability coverage of 53.7%, with 51.9% achieving full coverage; mean noise-path rate was 83.9%. With median end-to-end time of 24.9 s (MulVAL reasoning: 2.7 s) the pipeline is feasible and runtime-practical for agentic workflows, but predicate coverage, rule coverage, and path precision remain limiting factors. Next steps include semantic rule validation and agent-level comparison for graph-guided pentesting.
Text extracted automatically; images, tables and formatting may be missing. Original: https://arxiv.org/abs/2609.15523