Pith. sign in

REVIEW 8 cited by

Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility Tree

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2507.14799 v1 pith:AHEDAF3O submitted 2025-07-20 cs.CR cs.AI

Manipulating LLM Web Agents with Indirect Prompt Injection Attack via HTML Accessibility Tree

classification cs.CR cs.AI
keywords agentshtmlaccessibilityagentattacksdemonstratesgithubindirect
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

This work demonstrates that LLM-based web navigation agents offer powerful automation capabilities but are vulnerable to Indirect Prompt Injection (IPI) attacks. We show that adversaries can embed universal adversarial triggers in webpage HTML to hijack agent behavior that utilizes the accessibility tree to parse HTML, causing unintended or malicious actions. Using the Greedy Coordinate Gradient (GCG) algorithm and a Browser Gym agent powered by Llama-3.1, our system demonstrates high success rates across real websites in both targeted and general attacks, including login credential exfiltration and forced ad clicks. Our empirical results highlight critical security risks and the need for stronger defenses as LLM-driven autonomous web agents become more widely adopted. The system software (https://github.com/sej2020/manipulating-web-agents) is released under the MIT License, with an accompanying publicly available demo website (http://lethaiq.github.io/attack-web-llm-agent).

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. From Monoliths to Swarms: A Study of Attack Surface Evolution in the Transition to Multi-Agent Web Systems

    cs.CR 2026-07 conditional novelty 7.0

    A new 'Telephone Loop' attack stalls multi-agent web systems in delegation cycles, succeeding in about 80% of baseline runs for three frontier models while failing against single-agent systems.

  2. SecureWebArena: A Holistic Security Evaluation Benchmark for LVLM-based Web Agents

    cs.CR 2025-10 unverdicted novelty 7.0

    SecureWebArena is a new benchmark suite for holistic security evaluation of LVLM-based web agents using diverse simulated environments, attack taxonomies, and multi-layered failure analysis across reasoning, behavior,...

  3. Agent Security Needs Redefinition through a Holistic Framework

    cs.CR 2026-07 conditional novelty 6.0

    Agent security should be redefined around four contextual authorization properties instead of the content of the action performed.

  4. Security Considerations for Multi-agent Systems

    cs.CR 2026-03 unverdicted novelty 6.0

    No existing AI security framework covers a majority of the 193 identified multi-agent system threats in any category, with OWASP Agentic Security Initiative achieving the highest overall coverage at 65.3%.

  5. Agent Security is a Systems Problem

    cs.CR 2026-05 unverdicted novelty 5.0

    Agent security must be treated as a systems problem by viewing the AI model as untrusted and applying established systems security principles to enforce invariants.

  6. A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron?

    cs.CL 2025-05 unverdicted novelty 5.0

    A survey that defines Computer-Using Agents for safety analysis, categorizes their threats, proposes a taxonomy of defensive strategies, and summarizes benchmarks and datasets for evaluating CUA safety and performance.

  7. Agent Security is a Systems Problem

    cs.CR 2026-05 unverdicted novelty 4.0

    The paper argues that agent security is best addressed as a systems problem by applying principles from operating systems, networks, and formal methods rather than relying solely on model robustness improvements.

  8. Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges

    cs.AI 2025-10 unverdicted novelty 4.0

    A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.