LoginTrap induces LLM-based web agents to enter attacker-controlled login flows and submit sensitive information, achieving 86% average end-to-end success across LLM backbones.
Car- bon: domain-independent automatic web form filling
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
other 1
citation-polarity summary
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1roles
other 1polarities
unclear 1representative citing papers
citing papers explorer
-
LoginTrap: Uncovering Task-Agnostic Phishing-Style Indirect Prompt Injection Attacks against LLM-based Web Agents
LoginTrap induces LLM-based web agents to enter attacker-controlled login flows and submit sensitive information, achieving 86% average end-to-end success across LLM backbones.