QRS: A Rule-Synthesizing Neuro-Symbolic Triad for Autonomous Vulnerability Discovery

TL;DR

QRS is a neuro-symbolic framework that uses autonomous agents and large language models to generate and validate security queries, enabling the discovery of new vulnerabilities beyond predefined patterns with high accuracy.

Contribution

It introduces a novel neuro-symbolic approach that synthesizes CodeQL queries from structured schemas and examples, improving vulnerability detection beyond existing static analysis tools.

Findings

Achieved 90.6% detection accuracy on historical CVEs

Identified 39 new vulnerabilities in popular PyPI packages

Validated the approach with low overhead and high discoverability

Abstract

Static Application Security Testing (SAST) tools are integral to modern DevSecOps pipelines, yet tools like CodeQL, Semgrep, and SonarQube remain fundamentally constrained: they require expert-crafted queries, generate excessive false positives, and detect only predefined vulnerability patterns. Recent work has explored augmenting SAST with Large Language Models (LLMs), but these approaches typically use LLMs to triage existing tool outputs rather than to reason about vulnerability semantics directly. We introduce QRS (Query, Review, Sanitize), a neuro-symbolic framework that inverts this paradigm. Rather than filtering results from static rules, QRS employs three autonomous agents that generate CodeQL queries from a structured schema definition and few-shot examples, then validate findings through semantic reasoning and automated exploit synthesis. This architecture enables QRS to discover vulnerability classes beyond predefined patterns while substantially reducing false positives. We evaluate QRS on full Python packages rather than isolated snippets. In 20 historical CVEs in popular PyPI libraries, QRS achieves 90.6% detection accuracy. Applied to the 100 most-downloaded PyPI packages, QRS identified 39 medium-to-high-severity vulnerabilities, 5 of which were assigned new CVEs, 5 received documentation updates, while the remaining 29 were independently discovered by concurrent researchers, validating both the severity and discoverability of these findings. QRS accomplishes this with low time overhead and manageable token costs, demonstrating that LLM-driven query synthesis and code review can complement manually curated rule sets and uncover vulnerability patterns that evade existing industry tools.