VATS: Exploiting Implicit Authority in Error-Path Injection via Systematic Mutation

Computer Science > Artificial Intelligence [Submitted on 6 Jun 2026] VATS: Exploiting Implicit Authority in Error-Path Injection via Systematic Mutation Harshil Patel, Kunal Pai As the Model Context Protocol (MCP) standardizes tool-calling for autonomous agents, it introduces a critical, unexamined attack surface: the error-handling loop. We hypothesize that tool error messages possess implicit authority, triggering corrective reasoning modes that bypass standard safety heuristics. We introduce VATS (Vulnerability Analysis of Tool Streams), a mutation-driven framework that systematically evolves adversarial payloads across seven structural and linguistic dimensions. Our evaluation across four frontier models, Gemini 3.1 Pro, GPT-5.5, GLM-5.1, and Qwen3-Coder, demonstrates that error-path injection triples the success rate of standard indirect prompt injection (IPI), achieving up to 100% compliance in controlled evaluations. We isolate structural positioning (sandwiching instructions within error context) as the most effective exploit vector across all tested models. While we find that production framework guardrails can mitigate these vulnerabilities, the inherent susceptibility of the model layer poses a systemic risk to bespoke agentic workflows. Comments: Published at Second Workshop on Agents in the Wild: Safety, Security, and Beyond (ICML 2026 AIWILD) Subjects: Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Software Engineering (cs.SE) Cite as: arXiv:2606.07992 [cs.AI]   (or arXiv:2606.07992v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.07992 Focus to learn more Submission history From: Harshil Patel [view email] [v1] Sat, 6 Jun 2026 06:07:52 UTC (210 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.CR cs.SE References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)