AgentXploit-Bench

Search everything

Mentions · 7d0
Mentions · 30d0
All mentions1
First seenSep 25, 2026
Last mentionedSep 25, 2026

Timeline

1 articles · newest first

AgentXploit: Autonomous Repository-to-Runtime Red-Teaming for AI Agents

AgentXploit audits AI-agent repos into confirmed runtime attacks, reaching 59.3% success on 72 benchmark bugs.

arXiv cs.CRSep 25, 14:26 UTC · Sep 25, 2026AI safety & security2 · 2 reads

Appears with

AgentVigilproduct · 1
AgentXploitproduct · 1
AgentDojoproduct · 1
Codexproduct · 1

Entities are extracted by the model from each article. First seen Sep 25, 2026, last mentioned Sep 25, 2026. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.