Source record

Published by arXiv cs.HC (T1 source). The original is at https://arxiv.org/abs/2607.15143.

Pipeline notes

The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.

Research paper showing that AI coding agents can be exploited through ordinary setup documentation such as READMEs, requirements files, and Makefiles. Across 12 scenarios in 5 attack classes, registries are redirected, vulnerable versions installed, and typosquats accepted; security depends on the model-harness pairing. A deterministic pre-install name, source, and version check closes most of the gap.

Names a concrete attack surface in agent-driven project setup and points to a specific defensive pattern, useful to anyone wiring coding agents into real repositories.

Cited by

• Safe models do not compose into safe systems