English

LLM-Enabled Open-Source Systems in the Wild: An Empirical Study of Vulnerabilities in GitHub Security Advisories

Cryptography and Security 2026-04-16 v2 Software Engineering

Abstract

Large language models (LLMs) are increasingly embedded in open-source software (OSS) ecosystems, creating complex interactions among natural language prompts, probabilistic model outputs, and execution-capable components. However, it remains unclear whether traditional vulnerability disclosure frameworks adequately capture these model-mediated risks. To investigate this, we analyze 295 GitHub Security Advisories published between January 2025 and January 2026 that reference LLM-related components, and we manually annotate a sample of 100 advisories using the OWASP Top 10 for LLM Applications 2025. We find no evidence of new implementation-level weakness classes specific to LLM systems. Most advisories map to established CWEs, particularly injection and deserialization weaknesses. At the same time, the OWASP-based analysis reveals recurring architectural risk patterns, especially Supply Chain, Excessive Agency, and Prompt Injection, which often co-occur across multiple stages of execution. These results suggest that existing advisory metadata captures code-level defects but underrepresents model-mediated exposure. We conclude that combining the CWE and OWASP perspectives provides a more complete and necessary view of vulnerabilities in LLM-integrated systems.

Keywords

Cite

@article{arxiv.2604.04288,
  title  = {LLM-Enabled Open-Source Systems in the Wild: An Empirical Study of Vulnerabilities in GitHub Security Advisories},
  author = {Fariha Tanjim Shifat and Hariswar Baburaj and Ce Zhou and Jaydeb Sarker and Mia Mohammad Imran},
  journal= {arXiv preprint arXiv:2604.04288},
  year   = {2026}
}

Comments

The 2nd International Workshop on Large Language Model Supply Chain Analysis (LLMSC 2026)

R2 v1 2026-07-01T11:54:44.706Z