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

arXiv: https://arxiv.org/abs/2607.23624 · HTML: https://mlsanity.com/paper/2607.23624/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 32 of its 39 references that are in the map.
- First posted on arXiv 26 Jul 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 30 of 32)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Prompt Injection Attack to Tool Selection in LLM Agents](https://mlsanity.com/paper/2504.19793/) (2025)
- [Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories](https://mlsanity.com/paper/2506.18824/) (2025)
- [ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback](https://mlsanity.com/paper/2601.10156/) (2026)
- [You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projects](https://mlsanity.com/paper/2412.10133/) (2024)
- [Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems](https://mlsanity.com/paper/2604.03081/) (2026)
- [Human-In-the-Loop Software Development Agents](https://mlsanity.com/paper/2411.12924/) (2024)
- [Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems](https://mlsanity.com/paper/2604.14228/) (2026)
- [The Attack and Defense Landscape of Agentic AI: A Comprehensive Survey](https://mlsanity.com/paper/2603.11088/) (2026)
- [AgentBound: Securing Execution Boundaries of AI Agents](https://mlsanity.com/paper/2510.21236/) (2025)
- [SoK: The Attack Surface of Agentic AI - Tools and Autonomy](https://mlsanity.com/paper/2603.22928/) (2026)
- [SafeHarness: Lifecycle-Integrated Security Architecture for LLM-based Agent Deployment](https://mlsanity.com/paper/2604.13630/) (2026)
- [Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain](https://mlsanity.com/paper/2604.08407/) (2026)
- [AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments](https://mlsanity.com/paper/2606.10484/) (2026)
- [DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback](https://mlsanity.com/paper/2605.22781/) (2026)
- [Life-Cycle Routing Vulnerabilities of LLM Router](https://mlsanity.com/paper/2503.08704/) (2025)
- [Why AI Agents Still Need You: Findings from Developer-Agent Collaborations in the Wild](https://mlsanity.com/paper/2506.12347/) (2025)
- [Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks](https://mlsanity.com/paper/2603.30016/) (2026)
- [Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills](https://mlsanity.com/paper/2606.07412/) (2026)
- [Real Money, Fake Models: Deceptive Model Claims in Shadow APIs](https://mlsanity.com/paper/2603.01919/) (2026)
- [Authorization Propagation in Multi-Agent AI Systems: Identity Governance as Infrastructure](https://mlsanity.com/paper/2605.05440/) (2026)
- [Beyond Data Privacy: New Privacy Risks for Large Language Models](https://mlsanity.com/paper/2509.14278/) (2025)
- [Red-Teaming Coding Agents from a Tool-Invocation Perspective: An Empirical Security Assessment](https://mlsanity.com/paper/2509.05755/) (2025)
- [Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization](https://mlsanity.com/paper/2604.15022/) (2026)
- [RerouteGuard: Understanding and Mitigating Adversarial Risks for LLM Routing](https://mlsanity.com/paper/2601.21380/) (2026)
- [LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents](https://mlsanity.com/paper/2606.20529/) (2026)
- [Auditing MCP Servers for Over-Privileged Tool Capabilities](https://mlsanity.com/paper/2603.21641/) (2026)
- [AgentWard: A Lifecycle Security Architecture for Autonomous AI Agents](https://mlsanity.com/paper/2604.24657/) (2026)

## Abstract (arXiv)

Third-party API routers have become a common layer that unifies access across increasingly diverse LLM providers. In coding-agent workflows, high-autonomy operation is widely adopted because it reduces interaction overhead. As a result, a third-party API router, which sits between the agent and the upstream provider, inevitably occupies the trusted path. It can inspect and modify every request and response, yet no mechanism verifies alignment between the provider's output and the repository-level actions ultimately executed by the agent. Consequently, client-side permission mechanisms may become ineffective in practice. Whether this control gap produces real, hard-to-detect effects on software development tasks remains empirically unmeasured. In this paper, we conduct an empirical study of router-side injection in coding agents, examining four intervention levels of increasing subtlety: Response Substitution (L1), Response Append (L2), LLM-Polished Injection (L3), and LLM-Polished with Distribution Alignment Injection (L4). Moreover, we develop SIDEL, a framework for trace recording, replay, injection, and defense evaluation, with a curated dataset of 400 samples. We evaluate four representative coding agents, and further evaluate whitelist-based execution control and LLM review. Router-side intervention substantially alters repository-level actions and remains difficult for existing client-side safeguards to detect. Without additional mitigations, all evaluated agents achieved a defense success rate of 0 percent across all injection levels. Client-side mitigations and reactive reviews improve resistance but do not fully restore end-to-end control, motivating provider-side output-integrity guarantees. Our code is available at https://github.com/Riyasushin/SIDEL.