# Automatically Attacking Software Reverse Engineering AI Agents

> A proof of concept for indirect prompt injection against Cline/GhidraMCP binary-analysis agents. An adapted AutoDAN generates embedded strings that make the agent describe different behavior. The authors demonstrate four small C programs with Qwen3-8B and transfer the examples to GPT-OSS-120B.

- Authors: Brian Crawford; Justin Phillips; Patrick McClure
- Venue: ECCWS 2026
- Status: Conference paper
- Publication / posting date: June 15, 2026
- Date source: Publisher and Crossref online publication date; arXiv submission is recorded separately.
- First arXiv submission: May 28, 2026
- arXiv: 2605.30667
- Reviewed arXiv version: v1
- DOI: 10.34190/eccws.25.1.4597
- Sources reviewed: 2026-10-19
- Added to the catalog: 2026-10-19
- Original paper: <https://papers.academic-conferences.org/index.php/eccws/article/view/4597>
- PDF: <https://papers.academic-conferences.org/index.php/eccws/article/download/4597/4412/17540>
- BibTeX: <https://awesomerea.org/papers/citations/paper-attacking-re-ai-agents.bib>
- Catalog page: <https://awesomerea.org/papers/paper-attacking-re-ai-agents/>
- Record JSON: <https://awesomerea.org/papers/paper-attacking-re-ai-agents/record.json>
- Chinese version: [简体中文](https://awesomerea.org/zh/papers/paper-attacking-re-ai-agents/index.md)

## Scope and limitations

Four illustrative programs, each with one or two functions; no repeated-trial success rate, realistic malware corpus or defense evaluation. The reported decompiler setting truncates strings beyond 2,048 characters. These examples do not establish general reliability across models or complex binaries.

## Why it fits this collection

Adds direct evidence of a trust-boundary failure in agent-assisted reverse engineering.

## Publication and review notes

ECCWS proceedings, pages 199–205; Crossref labels its deposit journal-article. Author order agrees across publisher, Crossref and arXiv. No implementation or dataset is linked in the reviewed primary sources.

## Primary sources

1. <https://papers.academic-conferences.org/index.php/eccws/article/view/4597>
2. <https://papers.academic-conferences.org/index.php/eccws/article/download/4597/4412/17540>
3. <https://api.crossref.org/works/10.34190/eccws.25.1.4597>
4. <https://arxiv.org/abs/2605.30667v1>
5. <https://arxiv.org/pdf/2605.30667v1>

## About this entry

Reviewed against the paper and its primary sources. Cite the original authors using the linked paper or BibTeX.
Original editorial content: MIT. Linked projects, papers and assets retain their own rights and licenses.