Skip to content
We Ran 1,060 Autonomous Attacks. Here's What the Industry Gets Wrong.
xbow.com | blog | #ai-security | #vulnerability-research | #ai-safety | #benchmark | #llm | #hackerone | #autonomous-attacks
Summary
Counters the 2026 International AI Safety Report's claim that autonomous attacks aren't feasible yet, citing XBOW's record: 1,060 HackerOne vulns, 48-step chains, a 40-hour job in 28 minutes.
- Published
- Collected