WASP benchmark reveals web agents are vulnerable to simple prompt injections with partial success rates up to 86%, but agents frequently fail to complete attacker objectives.
Answer: [NA] Justification: We do not use LLMs in any special way covered by the policy
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
WASP benchmark reveals web agents are vulnerable to simple prompt injections with partial success rates up to 86%, but agents frequently fail to complete attacker objectives.