[2608.05223] Towards a Risk Assessment of Malicious Skill Files in Coding Agents

Skip to main content

Search arXiv

Press Enter to search · Advanced search

-->

Computer Science > Software Engineering

arXiv:2608.05223 (cs)

[Submitted on 5 Aug 2026]

Title:Towards a Risk Assessment of Malicious Skill Files in Coding Agents

Authors:Rui Yang, Michael Fu, Kla Tantithamthavorn, Chetan Arora, Joey Chua<br>View a PDF of the paper titled Towards a Risk Assessment of Malicious Skill Files in Coding Agents, by Rui Yang and 4 other authors

View PDF<br>HTML (experimental)

Abstract:Autonomous coding agents are increasingly embedded in enterprise software workflows with delegated authority over connected systems. Central to this architecture is the agent skills interface: folders of instructions and scripts that agents load dynamically to specialize their behavior. This interface also widens the attack surface, letting malicious shell commands hide within natural-language skill files. We make three contributions. First, an adversarial skill-synthesis method using six LLMs across four families to transform 471 real-world shell commands into benign-appearing skills, released as a benchmark of 2,826 skills mapped to 11 MITRE ATT&CK tactics. Second, a reproducible evaluation pipeline coupling run stratification, evidence anchoring, a refusal veto, and a deterministic declared-intent override with a three-judge LLM-as-a-judge panel, validated against a blind human gold standard (Cohen's kappa = 0.85). Third, a large-scale characterization of two enterprise-grade agents across 5,629 completed runs. Gemini CLI is exploited in 95.5-96.1% of runs and Qwen Code in 71.6-74.0% (raw majority vote to declared-intent-corrected estimate, both within the human gold standard), nearly invariant to the generating model. Explicit safety recognition occurs in only 1.99% of runs. Enterprises must assess and mitigate skill-interface risk before adopting coding agents. Our code and dataset are available at this https URL

Comments:<br>29 pages, 6 figures, 6 tables. Preprint; under review

Subjects:

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

ACM classes:<br>D.4.6; D.2.4; I.2.7; K.6.5

Cite as:<br>arXiv:2608.05223 [cs.SE]

(or<br>arXiv:2608.05223v1 [cs.SE] for this version)

https://doi.org/10.48550/arXiv.2608.05223

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Rui Yang [view email]<br>[v1]<br>Wed, 5 Aug 2026 11:33:43 UTC (1,042 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Towards a Risk Assessment of Malicious Skill Files in Coding Agents, by Rui Yang and 4 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 allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

Which authors of this paper are endorsers? |<br>Disable MathJax (What is MathJax?)

Major funding support from