Does Fixing Break Security? An Empirical Study of LLM Security Degradation

Jimmc4141 pts0 comments

[2608.13404] Does Fixing Break Security? An Empirical Study of Security Degradation in Iterative LLM-Driven Infrastructure-as-Code Repair

Skip to main content

Search arXiv

Press Enter to search · Advanced search

-->

Computer Science > Software Engineering

arXiv:2608.13404 (cs)

[Submitted on 13 Aug 2026]

Title:Does Fixing Break Security? An Empirical Study of Security Degradation in Iterative LLM-Driven Infrastructure-as-Code Repair

Authors:Benjamin Agyekum, Fabio Santos<br>View a PDF of the paper titled Does Fixing Break Security? An Empirical Study of Security Degradation in Iterative LLM-Driven Infrastructure-as-Code Repair, by Benjamin Agyekum and 1 other authors

View PDF<br>HTML (experimental)

Abstract:Background: Iterative feedback loops are the dominant paradigm for improving LLM-generated Infrastructure-as-Code (IaC): validators such as Checkov and terraform validate feed error signals back for successive repair attempts. Prior work reports cumulative-best metrics, which are non-decreasing by construction, so the raw per-iteration security trajectory has never been examined for IaC. Aims: We study security regression (a previously-passing CIS Benchmark check that fails after a repair iteration) to determine whether and how often iterative LLM repair degrades security while fixing other issues. Method: We analyze 5,968 scenario timelines from the IaC-Eval benchmark, each one scenario run through one configuration for up to 5 repair iterations. The 15 configurations (six model-specific RAG, nine model-aggregated non-RAG, three temperatures each) yield 4,440 iteration transitions with Checkov data on both sides. We track 30 individual CIS check IDs and classify root causes from code diffs, under two detection modes: standard (inclusive) and strict (exclusive check failures only). Results: Under standard detection, 13.8% of scenarios (24.8% of transitions) exhibit at least one regression. Under strict detection the rate falls to 3.3% of scenarios (5.2% of transitions), indicating most apparent regressions are multi-resource measurement artifacts. Resource restructuring (79.0%) is the dominant root cause. Regression transitions show 2.6x more code churn (Cohen's d=0.90) and 4.9x higher strict-mode check volatility (d=1.49). Of standard-mode regressions, 36.6% self-correct within an average of 1.2 iterations; iteration 3 is the optimal stopping point. Conclusions: Iterative IaC repair does introduce security regressions, but the conservative, defensible rate is about 3.3% of scenarios. Our findings motivate security-aware feedback-loop design and actionable iteration-budget guidance.

Comments:<br>20 pages, 3 figures, 5 tables. Accepted at the 20th International Symposium on Empirical Software Engineering and Measurement (ESEM 2026). To appear in LIPIcs Vol. 394

Subjects:

Software Engineering (cs.SE); Cryptography and Security (cs.CR)

ACM classes:<br>D.2.5; D.2.4; K.6.5

Cite as:<br>arXiv:2608.13404 [cs.SE]

(or<br>arXiv:2608.13404v1 [cs.SE] for this version)

https://doi.org/10.48550/arXiv.2608.13404

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Benjamin Agyekum [view email]<br>[v1]<br>Thu, 13 Aug 2026 16:01:32 UTC (306 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Does Fixing Break Security? An Empirical Study of Security Degradation in Iterative LLM-Driven Infrastructure-as-Code Repair, by Benjamin Agyekum and 1 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.SE

next >

new<br>recent<br>| 2026-08

Change to browse by:

cs<br>cs.CR

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that...

security toggle code repair iterative fixing

Related Articles