Web agents with protected prompts can still be hijacked by injecting malicious steps into their stored task plans, reaching up to 63% success on privacy leaks.
Accessed: 2025- 05-21
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Context manipulation attacks : Web agents are susceptible to corrupted memory
Web agents with protected prompts can still be hijacked by injecting malicious steps into their stored task plans, reaching up to 63% success on privacy leaks.