{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/ras-eval-a-comprehensive-benchmark-for","title":"RAS-Eval: A Comprehensive Benchmark for Security Evaluation of LLM Agents in Real-World Environments","arxiv_id":"2506.15253","date":"2025-06-18","proceeding":null,"authors":["Yuchuan Fu","Xiaohan Yuan","Dongxia Wang"],"abstract":"The rapid deployment of Large language model (LLM) agents in critical domains like healthcare and finance necessitates robust security frameworks. To address the absence of standardized evaluation benchmarks for these agents in dynamic environments, we introduce RAS-Eval, a comprehensive security benchmark supporting both simulated and real-world tool execution. RAS-Eval comprises 80 test cases and 3,802 attack tasks mapped to 11 Common Weakness Enumeration (CWE) categories, with tools implemented in JSON, LangGraph, and Model Context Protocol (MCP) formats. We evaluate 6 state-of-the-art LLMs across diverse scenarios, revealing significant vulnerabilities: attacks reduced agent task completion rates (TCR) by 36.78% on average and achieved an 85.65% success rate in academic settings. Notably, scaling laws held for security capabilities, with larger models outperforming smaller counterparts. Our findings expose critical risks in real-world agent deployments and provide a foundational framework for future security research. Code and data are available at https://github.com/lanzer-tree/RAS-Eval.","url_abs":"https://arxiv.org/abs/2506.15253v1","url_pdf":"https://arxiv.org/pdf/2506.15253v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"ras-eval-a-comprehensive-benchmark-for","repo_url":"https://github.com/lanzer-tree/ras-eval","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2506.15253","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.15253"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lanzer-tree/ras-eval","reach":{"status":"ok"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":4,"samples":[{"code_sha256_prefix":"b188fb6f2c679b64","entry":"camel_to_snake","repo":"lanzer-tree/ras-eval","repo_kind":"official","path":"src/utils/eval_utils.py","file_url":"https://github.com/lanzer-tree/ras-eval/blob/HEAD/src/utils/eval_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b188fb6f2c679b64"}},{"code_sha256_prefix":"bbd67e3d9b019a32","entry":"is_subsequence","repo":"lanzer-tree/ras-eval","repo_kind":"official","path":"src/utils/eval_utils.py","file_url":"https://github.com/lanzer-tree/ras-eval/blob/HEAD/src/utils/eval_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bbd67e3d9b019a32"}},{"code_sha256_prefix":"200b38ee81fbfae6","entry":"parse_toolkits","repo":"lanzer-tree/ras-eval","repo_kind":"official","path":"src/utils/benchmark_utils.py","file_url":"https://github.com/lanzer-tree/ras-eval/blob/HEAD/src/utils/benchmark_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"200b38ee81fbfae6"}},{"code_sha256_prefix":"ad10cae899b745f1","entry":"response_failure_mode_analysis","repo":"lanzer-tree/ras-eval","repo_kind":"official","path":"src/utils/eval_utils.py","file_url":"https://github.com/lanzer-tree/ras-eval/blob/HEAD/src/utils/eval_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ad10cae899b745f1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}