RECEIPT: Deterministic, Reward-Hacking-Resistant Verification for White-Box Agentic XSS Discovery

• URL: http://arxiv.org/abs/2607.18575v1
• Date: Mon, 20 Jul 2026 23:16:16 GMT
• Title: RECEIPT: Deterministic, Reward-Hacking-Resistant Verification for White-Box Agentic XSS Discovery
• Abstract summary: Cross-Site Scripting (XSS) remains one of the most prevalent and damaging classes of web vulnerabilities.<n>We present RECEIPT, a verification framework that makes agent-reported XSS findings trustworthy.
• Score: 8.773382962696136
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cross-Site Scripting (XSS) remains one of the most prevalent and damaging classes of web vulnerabilities. LLM-based coding agents offer a promising approach to XSS discovery by combining source-code reasoning with interactive testing against a running application. However, a coding agent's claims cannot be trusted on their own. We characterize three reward-hacking behaviors in white-box agentic XSS discovery and propose three requirements that an ideal verifier should meet. We present RECEIPT, a verification framework that makes agent-reported XSS findings trustworthy by enforcing environment isolation, PoC constraints, role separation, and verdict binding. Each confirmation therefore establishes two properties: the script runs in a real browser, and the payload was planted under the attacker role and executed in the victim role's browser. This constrained replay procedure makes validation deterministic and reproducible. We evaluate RECEIPT on 95 real-world web-application targets drawn from popular open-source projects. Within a $20 per-application budget, RECEIPT found 24 previously unknown XSS vulnerabilities, 12 of which have already been acknowledged by maintainers after responsible disclosure, and recovered the labeled CVE in 36% of known-vulnerability recovery targets. Compared with the same agent using self-judgment and with black-box scanners, RECEIPT confirms more real exploits while admitting no false positives.

Related papers

• SIR: Self-improving Red-teaming for Compute Use Agents [71.71987044117371]
  Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal.<n>Because they can be exposed to untrusted content while operating, they are vulnerable to indirect prompt injection (IPI)<n>We present SIR, a black box IPI attack that composes stealthy injections from a small library of reusable principles stated in plain language.
  arXiv  Detail & Related papers  (2026-08-31T03:39:43Z)
• SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response [38.89333299127352]
  We introduce SecRespond, the first benchmark for evaluating Large Language Model (LLM) agents on the post-compromise incident-response workflow.<n>We instantiate this task across 10 cyber ranges, each constructed from a distinct compromised cloud host.<n> Experimental results show that although current agents can reliably uncover the problems exposed by alerts, they struggle to proactively investigate the disk for silent intrusions.
  arXiv  Detail & Related papers  (2026-07-29T11:32:23Z)
• Agent Hacks Agent: Autoresearch for Production-Agent Red-Teaming [8.592488240217625]
  We study automated red-teaming for production LLM agents using one agentic research environment.<n>We present AHA, a falsifiable discovery loop that proposes a vulnerability hypothesis, constructs a falsifier, instantiates a valid attack, executes it in a sandboxed harness, and promotes confirmed findings into a Vulnerability Concept Graph (VCG)<n>Across Claude Code and Codex on three scenarios covering direct and indirect attacks, the discovered concepts reveal a reusable vulnerability core across models and agents.
  arXiv  Detail & Related papers  (2026-07-13T15:31:04Z)
• Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens [65.53494487819053]
  Claw-like AI agents (e.g., OpenClaw) are always-on processes with persistent access to credentials, files, tools, and external services.<n>We adopt a computer-system analogy: treating a Claw-like agent as an agentic computer system whose gateway runtime plays an OS-like mediation role.<n>We develop SafeClawArena, a benchmark of 406 adversarial tasks across four attack surfaces.
  arXiv  Detail & Related papers  (2026-06-29T18:00:45Z)
• ClawSafety: "Safe" LLMs, Unsafe Agents [25.729388843970014]
  Personal AI agents like OpenClaw run with elevated privileges on users' local machines.<n>ClawSAFETY is a benchmark of 120 adversarial test scenarios organized along three dimensions (harm domain, attack vector, and harmful action type)<n>Each test case embeds adversarial content in one of three channels the agent encounters during normal work: workspace skill files, emails from trusted senders, and web pages.
  arXiv  Detail & Related papers  (2026-04-01T22:24:24Z)
• AXE: An Agentic eXploit Engine for Confirming Zero-Day Vulnerability Reports [9.184243224127377]
  Agentic eXploit Engine (AXE) is a multi-agent framework for Web application exploitation.<n>AXE achieves a 30% exploitation success rate, a 3x improvement over state-of-the-art black-box baselines.<n>For successful exploits, AXE produces actionable, reproducible proof-of-concept artifacts.
  arXiv  Detail & Related papers  (2026-02-15T23:25:14Z)
• 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)
• The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search [58.8834056209347]
  Large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs.<n>We introduce the Correlated Knowledge Attack Agent (CKA-Agent), a dynamic framework that reframes jailbreaking as an adaptive, tree-structured exploration of the target model's knowledge base.
  arXiv  Detail & Related papers  (2025-12-01T07:05:23Z)
• RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents [70.24175620901538]
  Code agents have gained widespread adoption due to their strong code generation capabilities and integration with code interpreters.<n>Current static safety benchmarks and red-teaming tools are inadequate for identifying emerging real-world risky scenarios.<n>We propose RedCodeAgent, the first automated red-teaming agent designed to systematically uncover vulnerabilities in diverse code agents.
  arXiv  Detail & Related papers  (2025-10-02T22:59:06Z)
• SecureAgentBench: Benchmarking Secure Code Generation under Realistic Vulnerability Scenarios [17.276786247873613]
  SecureAgentBench is a benchmark of 105 coding tasks designed to rigorously evaluate code agents' capabilities in secure code generation.<n>Results show that (i) current agents struggle to produce secure code, as even the best-performing one, SWE-agent supported by DeepSeek-V3.1, achieves merely 15.2% correct-and-secure solutions.
  arXiv  Detail & Related papers  (2025-09-26T09:18:57Z)
• VulAgent: Hypothesis-Validation based Multi-Agent Vulnerability Detection [55.957275374847484]
  VulAgent is a multi-agent vulnerability detection framework based on hypothesis validation.<n>It implements a semantics-sensitive, multi-view detection pipeline, each aligned to a specific analysis perspective.<n>On average, VulAgent improves overall accuracy by 6.6%, increases the correct identification rate of vulnerable--fixed code pairs by up to 450%, and reduces the false positive rate by about 36%.
  arXiv  Detail & Related papers  (2025-09-15T02:25:38Z)
• Dancer in the Dark: Synthesizing and Evaluating Polyglots for Blind Cross-Site Scripting [10.696934248458136]
  Cross-Site Scripting (XSS) is a prevalent and well known security problem in web applications.<n>We present the first comprehensive study on blind XSS (BXSS)<n>We develop a method for synthesizing polyglots, small XSS payloads that execute in all common injection contexts.
  arXiv  Detail & Related papers  (2025-02-12T15:02:30Z)
• Dissecting Adversarial Robustness of Multimodal LM Agents [70.2077308846307]
  We manually create 200 targeted adversarial tasks and evaluation scripts in a realistic threat model on top of VisualWebArena.<n>We find that we can successfully break latest agents that use black-box frontier LMs, including those that perform reflection and tree search.<n>We also use ARE to rigorously evaluate how the robustness changes as new components are added.
  arXiv  Detail & Related papers  (2024-06-18T17:32:48Z)

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.