Metraipolis › archive › dc_cd6838871f2a

Security Impact of Coding Agent's Memory Files — arXiv:2610.38521

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.38521
License (as archived)
CC0-1.0
Archived
2026-11-01T02:21:24.401Z
SHA-256 of the archived text
f99cbd7899c29576bc03ff55f11db1212f8153e727dc19cea95c71ab88a6b14e
Stable URL of this page
https://metraipolis.com/documento/dc_cd6838871f2a

How to cite

Security Impact of Coding Agent's Memory Files — arXiv:2610.38521 — arXiv (en), https://arxiv.org/abs/2610.38521 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd6838871f2a (Metraipolis archive dc_cd6838871f2a, sha256 f99cbd7899c29576bc03ff55f11db1212f8153e727dc19cea95c71ab88a6b14e)
BibTeX
@misc{dccd6838871f2a,
  title = {Security Impact of Coding Agent's Memory Files — arXiv:2610.38521},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.38521},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd6838871f2a; sha256 f99cbd7899c29576bc03ff55f11db1212f8153e727dc19cea95c71ab88a6b14e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38521. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Coding agents automatically load project memory files such as this http URL at the start of every session and treat them as trusted project guidance. Anyone who can change such a file, for example through a pull request, can therefore steer the agent without ever touching the developer's prompt. We study memory files as an attack surface for insecure code generation and ask (1) whether a malicious memory file makes agents produce code that passes its tests but is vulnerable, and (2) whether agents disclose to the developer that the file shaped their code. For each of 12 CWE classes, we crafted two malicious memory files, a qualified variant that presents removing defensive checks as engineering best practice and a forceful variant that demands it. We ran Claude Code (Sonnet 5.5) and OpenCode (Qwen 3.8 27B, DeepSeek V4.1 Flash) on 36 SecRepoBench tasks with and without these files. The malicious files changed the rate of secure completions by -8 to +6 percentage points, with no consistent pattern across agents or variants. Agents differ sharply in what they tell the developer about the file. Claude Code names it in about two thirds of its final messages, whereas OpenCode mentions it almost exclusively in its reasoning trace, not in the final message the developer reads. Flagging the file as an attack does not reliably protect the code, as such agents still generated vulnerable code. We outline the larger studies needed to quantify this risk across agents and to design defenses.

Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno).
Categorie arXiv: Software Engineering (cs.SE) ; Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2610.38521 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-01T02:12:13.415Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).