EUVIMEDEUVIMED entdecken
Crossref

Trajectory-Level Security Debt in LLM Coding Agents

Prateek Kumar Rajput, Abdoul Kader Kabore, Yewei Song, Mélissa Tessa, Tailia Malloy, Jacques Klein, Tegawendé F. Bissyandé

Proceedings of the AAAI Symposium Series · 06.11.2026 · 10 (1) · 1104-1113

DOI: 10.1609/aaaiss.v10i1.43533 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Symposium Series, online erschienen am 06.11.2026. Verfasst von Prateek Kumar Rajput und 6 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

LLM coding agents can traverse hundreds of intermediate code states before submitting a solution. Evaluating only the final artifact leaves the evolution of security findings unmeasured. We introduce the Security Debt Line Integral (SDLI), which accumulates static-analysis risk when an agent reaches a new best test pass ratio. We instantiate it with four static application security testing (SAST) tools and study artifacts from 830 passing SWE-bench runs, 712 ProgramBench final workspaces, and 13 public MirrorCode trajectories. The two large populations use the final-state special case of SDLI. Two-tool Common Weakness Enumeration (CWE) class agreement occurs in 3.9% of SWE-bench runs and 26.2% of the 80 ProgramBench runs passing at least 90% of official tests. These are scanner findings, not validated vulnerability rates. Excluding three advisory-heavy classes reduces the latter rate to 6.2%. Same-task runs differ in their measured scores, while one reconstructed ProgramBench run exposes persistent findings from its first implementation write. A repair case study reduces the scanner signal while preserving tested behavior, but also reveals sensitivity to equivalent API rewrites. SDLI offers a way to study progress and security findings together. Its value for steering agents and confirming exploitable vulnerabilities remains to be established.

Zitieren

APA

Rajput, P. K., Kabore, A. K., Song, Y., Tessa, M., Malloy, T., Klein, J., & Bissyandé, T. F. (2026). Trajectory-Level Security Debt in LLM Coding Agents. Proceedings of the AAAI Symposium Series, 10(1), 1104-1113. https://doi.org/10.1609/aaaiss.v10i1.43533

Vancouver

Rajput PK, Kabore AK, Song Y, Tessa M, Malloy T, Klein J, et al. Trajectory-Level Security Debt in LLM Coding Agents. Proceedings of the AAAI Symposium Series. 2026;10(1):1104-1113. doi:10.1609/aaaiss.v10i1.43533

BibTeX
@article{Rajput2026,
  author = {Rajput, Prateek Kumar and Kabore, Abdoul Kader and Song, Yewei and Tessa, Mélissa and Malloy, Tailia and Klein, Jacques and Bissyandé, Tegawendé F.},
  title = {Trajectory-Level Security Debt in LLM Coding Agents},
  journal = {Proceedings of the AAAI Symposium Series},
  year = {2026},
  volume = {10},
  number = {1},
  pages = {1104--1113},
  doi = {10.1609/aaaiss.v10i1.43533}
}
Kostenlos starten →