Bonan Ruan

GitHub Continuous Integration (CI) workflows increasingly integrate Large Language Models (LLMs) to automate review, triage, content generation, and repository maintenance. This creates a new attack surface: externally controllable workflow inputs can shape LLM prompts and outputs, which may in turn affect security decisions, repository state, or privileged execution. Although LLM security and CI security have each been studied extensively, their intersection remains underexplored. In this paper, we present the first study of LLM-induced security risks in GitHub CI workflows. We characterize the problem along the full execution chain and develop a taxonomy of high-level risk classes and concrete threat vectors. To detect such risks in practice, we design Heimdallr, a hybrid analysis framework that normalizes workflows into an LLM-Workflow Property Graph (L-WPG) and combines triggerability analysis, LLM-assisted dataflow summarization, and deterministic propagation to synthesize concrete threat-vector findings. Evaluated on 300 manually annotated unique workflows, Heimdallr achieves high accuracy on LLM-node identification (F1 = 0.994), triggerability classification (99.8%), and threat-vector detection (micro-average F1 = 0.917). As part of an ongoing detection and disclosure effort, we have so far responsibly disclosed 802 vulnerable workflow instances across 759 repositories and received 71 acknowledgments.

Even though demonstrating extraordinary capabilities in code generation and software issue resolving, AI agents' capabilities in the full software DevOps cycle are still unknown. Different from pure code generation, handling the DevOps cycle in real-world software, including developing, deploying, and managing, requires analyzing large-scale projects, understanding dynamic program behaviors, leveraging domain-specific tools, and making sequential decisions. However, existing benchmarks focus on isolated problems and lack environments and tool interfaces for DevOps. We introduce DevOps-Gym, the first end-to-end benchmark for evaluating AI agents across core DevOps workflows: build and configuration, monitoring, issue resolving, and test generation. DevOps-Gym includes 700+ real-world tasks collected from 30+ projects in Java and Go. We develop a semi-automated data collection mechanism with rigorous and non-trivial expert efforts in ensuring the task coverage and quality. Our evaluation of state-of-the-art models and agents reveals fundamental limitations: they struggle with issue resolving and test generation in Java and Go, and remain unable to handle new tasks such as monitoring and build and configuration. These results highlight the need for essential research in automating the full DevOps cycle with AI agents.

LLM-based agents have demonstrated promising adaptability in real-world applications. However, these agents remain vulnerable to a wide range of attacks, such as tool poisoning and malicious instructions, that compromise their execution flow and can lead to serious consequences like data breaches and financial loss. Existing studies typically attempt to mitigate such anomalies by predefining specific rules and enforcing them at runtime to enhance safety. Yet, designing comprehensive rules is difficult, requiring extensive manual effort and still leaving gaps that result in false negatives. As agent systems evolve into complex software systems, we take inspiration from software system security and propose TraceAegis, a provenance-based analysis framework that leverages agent execution traces to detect potential anomalies. In particular, TraceAegis constructs a hierarchical structure to abstract stable execution units that characterize normal agent behaviors. These units are then summarized into constrained behavioral rules that specify the conditions necessary to complete a task. By validating execution traces against both hierarchical and behavioral constraints, TraceAegis is able to effectively detect abnormal behaviors. To evaluate the effectiveness of TraceAegis, we introduce TraceAegis-Bench, a dataset covering two representative scenarios: healthcare and corporate procurement. Each scenario includes 1,300 benign behaviors and 300 abnormal behaviors, where the anomalies either violate the agent’s execution order or break the semantic consistency of its execution sequence. Experimental results demonstrate that TraceAegis achieves strong performance on TraceAegis-Bench, successfully identifying the majority of abnormal behaviors. We further validate TraceAegis’ practicality through an internal redteaming process conducted within a technology company, where it effectively detects abnormal traces generated by red-team attacks.

Identifying the impact scope and scale is critical for software supply chain vulnerability assessment. However, existing studies face substantial limitations. First, prior studies either work at coarse package-level granularity producing many false positives or fail to accomplish whole-ecosystem vulnerability propagation analysis. Second, although vulnerability assessment indicators like CVSS characterize individual vulnerabilities, no metric exists to specifically quantify the dynamic impact of vulnerability propagation across software supply chains. To address these limitations and enable accurate and comprehensive vulnerability impact assessment, we propose a novel approach: (i) a hierarchical worklist-based algorithm for whole-ecosystem and call-graph-level vulnerability propagation analysis and (ii) the Vulnerability Propagation Scoring System (VPSS), a dynamic metric to quantify the scope and evolution of vulnerability impacts in software supply chains. We implement a prototype of our approach in the Java Maven ecosystem and evaluate it on 100 real-world vulnerabilities. Experimental results demonstrate that our approach enables effective ecosystem-wide vulnerability propagation analysis, and provides a practical, quantitative measure of vulnerability impact through VPSS.

PHP, a dominant scripting language in web development, powers a vast range of websites, from personal blogs to major platforms. While existing research primarily focuses on PHP application-level security issues like code injection, memory errors within the PHP interpreter have been largely overlooked. These memory errors, prevalent due to the PHP interpreter's extensive C codebase, pose significant risks to the confidentiality, integrity, and availability of PHP servers. This paper introduces FlowFusion, the first automatic fuzzing framework to detect memory errors in the PHP interpreter. FlowFusion leverages dataflow as an efficient representation of test cases maintained by PHP developers, merging two or more test cases to produce fused test cases with more complex code semantics. Moreover, FlowFusion employs strategies such as test mutation, interface fuzzing, and environment crossover to increase bug finding. In our evaluation, FlowFusion found 158 unknown bugs in the PHP interpreter, with 125 fixed and 11 confirmed. Comparing FlowFusion against the official test suite and a naive test concatenation approach, FlowFusion can detect new bugs that these methods miss, while also achieving greater code coverage. FlowFusion also outperformed state-of-the-art fuzzers AFL++ and Polyglot, covering 24% more lines of code after 24 hours of fuzzing. FlowFusion has gained wide recognition among PHP developers and is now integrated into the official PHP toolchain.

Linux kernel vulnerability reproduction is a critical task in system security. To reproduce a kernel vulnerability, the vulnerable environment and the Proof of Concept (PoC) program are needed. Most existing research focuses on the generation of PoC, while the construction of environment is overlooked. However, establishing an effective vulnerable environment to trigger a vulnerability is challenging. Firstly, it is hard to guarantee that the selected kernel version for reproduction is vulnerable, as the vulnerability version claims in online databases can occasionally be incorrect. Secondly, many vulnerabilities cannot be reproduced in kernels built with default configurations. Intricate non-default kernel configurations must be set to include and trigger a kernel vulnerability, but less information is available on how to recognize these configurations.

To solve these challenges, we propose a patch-based approach to identify real vulnerable kernel versions and a graph-based approach to identify necessary configs for activating a specific vulnerability. We implement these approaches in a tool, KernJC, automating the generation of vulnerable environments for kernel vulnerabilities. To evaluate the efficacy of KernJC, we build a dataset containing 66 representative real-world vulnerabilities with PoCs from kernel vulnerability research in the past five years. The evaluation shows that KernJC builds vulnerable environments for all these vulnerabilities, 32 (48.5%) of which require non-default configs, and 4 have incorrect version claims in the National Vulnerability Database (NVD). Furthermore, we conduct large-scale spurious version detection on kernel vulnerabilities and identify 128 vulnerabilities that have spurious version claims in NVD. To foster future research, we release KernJC with the dataset in the community.