arXiv:2610.38521 · v1

Security Impact of Coding Agent's Memory Files

首次提交 2026-10-28 17:33

版本更新 2026-10-28 17:33

雷达观测 2026-10-30 10:22

摘要

Coding agents automatically load project memory files such as CLAUDE.md 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.