Where Is the Tradeoff in Using Third-Party API Routers for Agentic Software Development?

The paper investigates how third‑party API routers, which sit between coding agents and large language model providers, can introduce a control gap by inspecting and modifying requests and responses. Through an empirical study using the SIDEL framework, the authors evaluate four levels of router‑side injection (Response Substitution, Response Append, LLM‑Polished Injection, and LLM‑Polished with Distribution Alignment Injection) across 400 curated samples and four representative coding agents. The results show that router‑side interventions significantly alter repository‑level actions and evade existing client‑side safeguards, achieving a 0% defense success rate without additional mitigations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• agents
• safety