{"slug": "guardrails-as-scapegoats-auditing-unfaithful-safety-refusals-in-tool-augmented", "title": "Guardrails as Scapegoats: Auditing Unfaithful Safety Refusals in Tool-Augmented", "summary": "A new study from researchers evaluating tool-augmented LLM agents finds that fabrication (FAR) dominates at 56.6% of valid responses when tools silently fail, while unfaithful safety refusals (USR) are nearly absent at baseline (0.25%) but amplify by 15.6x (to 3.95%) when the system prompt is augmented with standard safety language. The authors propose a payload-response misalignment heuristic for production-level detection and discuss governance implications for safety-forward deployments.", "body_md": "# Computer Science > Machine Learning\n\n[Submitted on 21 Jul 2026]\n\n# Title:Guardrails as Scapegoats: Auditing Unfaithful Safety Refusals in Tool-Augmented LLM Agents\n\n[View PDF](/pdf/2607.19449)\n\n[HTML (experimental)](https://arxiv.org/html/2607.19449v1)\n\nAbstract:Evaluation frameworks for tool-augmented LLM agents focus overwhelmingly on capability metrics or explicit tool crashes, leaving silent infrastructure failures and HTTP 200 responses with empty, null, or malformed payloads largely unaudited. We introduce a lightweight black-box auditing framework that injects four silent failure profiles across 12 production-adjacent tool stubs and classifies agent responses into three mutually exclusive behavioral classes: Honest Surrender (HSR), Fabrication (FAR), and Unfaithful Safety Refusal (USR). Evaluating two frontier and two open-source models at temperature zero under a neutral system prompt, we find that FAR dominates (56.6% of valid responses): agents treat empty payloads as real data, silently returning fabricated results. USR, in which an agent invents a policy or privacy rationale to explain the failure, is nearly absent at baseline (0.25%, one instance across 396 valid trajectories). Our key finding emerges from an ablation where we augment the system prompt with standard safety language (\"prioritize user privacy and data security\"), which amplifies USR by 15.6x (from 0.25% to 3.95%; 95% CI on ablation rate: 2.2%-6.4%; Fisher's exact test, p < 0.001). USR is a latent behavior, activated when safety vocabulary in the system prompt primes the model to reach for policy rationales when tools silently fail. Sensitive tools (fetch_medical_record, retrieve_contract, fetch_user_profile) account for the majority of USR instances. We propose a payload-response misalignment heuristic for production-level detection and discuss governance implications for safety-forward deployments.\n\n### Current browse context:\n\ncs.LG\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\nIArxiv Recommender\n\n*(*[What is IArxiv?](https://iarxiv.org/about))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/guardrails-as-scapegoats-auditing-unfaithful-safety-refusals-in-tool-augmented", "canonical_source": "https://arxiv.org/abs/2607.19449", "published_at": "2026-07-24 15:07:06+00:00", "updated_at": "2026-07-24 15:23:36.655352+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-safety", "ai-agents"], "entities": [], "alternates": {"html": "https://wpnews.pro/news/guardrails-as-scapegoats-auditing-unfaithful-safety-refusals-in-tool-augmented", "markdown": "https://wpnews.pro/news/guardrails-as-scapegoats-auditing-unfaithful-safety-refusals-in-tool-augmented.md", "text": "https://wpnews.pro/news/guardrails-as-scapegoats-auditing-unfaithful-safety-refusals-in-tool-augmented.txt", "jsonld": "https://wpnews.pro/news/guardrails-as-scapegoats-auditing-unfaithful-safety-refusals-in-tool-augmented.jsonld"}}