Penetration Testing of Agentic AI: A Comparative Security Analysis Across Models and Frameworks

• URL: http://arxiv.org/abs/2512.14860v1
• Date: Tue, 16 Dec 2025 19:22:50 GMT
• Title: Penetration Testing of Agentic AI: A Comparative Security Analysis Across Models and Frameworks
• Authors: Viet K. Nguyen, Mohammad I. Husain,
• Abstract summary: Agentic AI introduces security vulnerabilities that traditional LLM safeguards fail to address.<n>We conduct the first systematic testing and comparative evaluation of agentic AI systems.<n>We identify six distinct defensive behavior patterns including a novel "hallucinated compliance" strategy.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Agentic AI introduces security vulnerabilities that traditional LLM safeguards fail to address. Although recent work by Unit 42 at Palo Alto Networks demonstrated that ChatGPT-4o successfully executes attacks as an agent that it refuses in chat mode, there is no comparative analysis in multiple models and frameworks. We conducted the first systematic penetration testing and comparative evaluation of agentic AI systems, testing five prominent models (Claude 3.5 Sonnet, Gemini 2.5 Flash, GPT-4o, Grok 2, and Nova Pro) across two agentic AI frameworks (AutoGen and CrewAI) using a seven-agent architecture that mimics the functionality of a university information management system and 13 distinct attack scenarios that span prompt injection, Server Side Request Forgery (SSRF), SQL injection, and tool misuse. Our 130 total test cases reveal significant security disparities: AutoGen demonstrates a 52.3% refusal rate versus CrewAI's 30.8%, while model performance ranges from Nova Pro's 46.2% to Claude and Grok 2's 38.5%. Most critically, Grok 2 on CrewAI rejected only 2 of 13 attacks (15.4% refusal rate), and the overall refusal rate of 41.5% across all configurations indicates that more than half of malicious prompts succeeded despite enterprise-grade safety mechanisms. We identify six distinct defensive behavior patterns including a novel "hallucinated compliance" strategy where models fabricate outputs rather than executing or refusing attacks, and provide actionable recommendations for secure agent deployment. Complete attack prompts are also included in the Appendix to enable reproducibility.

Related papers

• ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack [52.17935054046577]
  We present ReasAlign, a model-level solution to improve safety alignment against indirect prompt injection attacks.<n>ReasAlign incorporates structured reasoning steps to analyze user queries, detect conflicting instructions, and preserve the continuity of the user's intended tasks.
  arXiv  Detail & Related papers  (2026-01-15T08:23:38Z)
• AI Security Beyond Core Domains: Resume Screening as a Case Study of Adversarial Vulnerabilities in Specialized LLM Applications [71.27518152526686]
  Large Language Models (LLMs) excel at text comprehension and generation, making them ideal for automated tasks like code review and content moderation.<n>LLMs can be manipulated by "adversarial instructions" hidden in input data, such as resumes or code, causing them to deviate from their intended task.<n>This paper introduces a benchmark to assess this vulnerability in resume screening, revealing attack success rates exceeding 80% for certain attack types.
  arXiv  Detail & Related papers  (2025-12-23T08:42:09Z)
• Towards a Science of Scaling Agent Systems [79.64446272302287]
  We formalize a definition for agent evaluation and characterize scaling laws as the interplay between agent quantity, coordination structure, modelic, and task properties.<n>We derive a predictive model using coordination metrics, that cross-validated R2=0, enabling prediction on unseen task domains.<n>We identify three effects: (1) a tool-coordination trade-off: under fixed computational budgets, tool-heavy tasks suffer disproportionately from multi-agent overhead, and (2) a capability saturation: coordination yields diminishing or negative returns once single-agent baselines exceed 45%.
  arXiv  Detail & Related papers  (2025-12-09T06:52:21Z)
• Securing AI Agents Against Prompt Injection Attacks [0.0]
  We present a benchmark for evaluating prompt injection risks in RAG-enabled AI agents.<n>Our framework reduces successful attack rates from 73.2% to 8.7% while maintaining 94.3% of baseline task performance.
  arXiv  Detail & Related papers  (2025-11-19T10:00:54Z)
• Jailbreak Mimicry: Automated Discovery of Narrative-Based Jailbreaks for Large Language Models [0.0]
  Large language models (LLMs) remain vulnerable to sophisticated prompt engineering attacks.<n>We introduce Jailbreak Mimicry, a systematic methodology for training compact attacker models to automatically generate narrative-based jailbreak prompts.<n>Our approach transforms adversarial prompt discovery from manual craftsmanship into a reproducible scientific process.
  arXiv  Detail & Related papers  (2025-10-24T23:53:16Z)
• Safeguarding Efficacy in Large Language Models: Evaluating Resistance to Human-Written and Algorithmic Adversarial Prompts [0.0]
  This paper presents a systematic security assessment of four prominent Large Language Models (LLMs) against adversarial attack vectors.<n>We evaluate Phi-2, Llama-2-7B-Chat, GPT-3.5-Turbo, and GPT-4 across four distinct attack categories: human-written prompts, AutoDAN, Greedy Coordinate Gradient (GCG), and Tree-of-Attacks-with-pruning (TAP)
  arXiv  Detail & Related papers  (2025-10-12T21:48:34Z)
• Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition [101.86739402748995]
  We run the largest public red-teaming competition to date, targeting 22 frontier AI agents across 44 realistic deployment scenarios.<n>We build the Agent Red Teaming benchmark and evaluate it across 19 state-of-the-art models.<n>Our findings highlight critical and persistent vulnerabilities in today's AI agents.
  arXiv  Detail & Related papers  (2025-07-28T05:13:04Z)
• When Developer Aid Becomes Security Debt: A Systematic Analysis of Insecure Behaviors in LLM Coding Agents [1.7587442088965226]
  LLM-based coding agents are rapidly being deployed in software development, yet their safety implications remain poorly understood.<n>We conducted the first systematic safety evaluation of autonomous coding agents, analyzing over 12,000 actions across five state-of-the-art models.<n>We developed a high-precision detection system that identified four major vulnerability categories, with information exposure the most prevalent.
  arXiv  Detail & Related papers  (2025-07-12T16:11:07Z)
• The Dark Side of LLMs: Agent-based Attacks for Complete Computer Takeover [0.0]
  Large Language Model (LLM) agents and multi-agent systems introduce security vulnerabilities that extend beyond traditional content generation to system-level compromises.<n>This paper presents a comprehensive evaluation of the LLMs security used as reasoning engines within autonomous agents.<n>We show how different attack surfaces and trust boundaries can be leveraged to orchestrate such takeovers.
  arXiv  Detail & Related papers  (2025-07-09T13:54:58Z)
• Let the Trial Begin: A Mock-Court Approach to Vulnerability Detection using LLM-Based Agents [10.378745306569053]
  VulTrial is a courtroom-inspired framework designed to enhance automated vulnerability detection.<n>It employs four role-specific agents, which are security researcher, code author, moderator, and review board.<n>Using GPT-3.5 and GPT-4o, VulTrial improves the performance by 102.39% and 84.17% over its respective baselines.
  arXiv  Detail & Related papers  (2025-05-16T07:54:10Z)
• AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security [74.22452069013289]
  AegisLLM is a cooperative multi-agent defense against adversarial attacks and information leakage.<n>We show that scaling agentic reasoning system at test-time substantially enhances robustness without compromising model utility.<n> Comprehensive evaluations across key threat scenarios, including unlearning and jailbreaking, demonstrate the effectiveness of AegisLLM.
  arXiv  Detail & Related papers  (2025-04-29T17:36:05Z)
• Malicious Agent Detection for Robust Multi-Agent Collaborative Perception [52.261231738242266]
  Multi-agent collaborative (MAC) perception is more vulnerable to adversarial attacks than single-agent perception. We propose Malicious Agent Detection (MADE), a reactive defense specific to MAC perception. We conduct comprehensive evaluations on a benchmark 3D dataset V2X-sim and a real-road dataset DAIR-V2X.
  arXiv  Detail & Related papers  (2023-10-18T11:36:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.