PPhying中文
Curated security research, vulnerabilities, advisories and tools for practitioners.

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
📄 Raw .md⬇️ Download .md🔗 Original ↗

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

Related coverage

blog · hackerone.com
Measuring The Fix: How We Evaluate Frontier Models on Remediation Quality
HackerOne tested frontier models on security fix quality and found the judge mattered more than the model. See how CTEM remediation earns engineer trust.
blog · tenzai.com
Five Models Walk Into an App Builder. Security Gets Interesting.
# Five Models Walk Into an App Builder. Security Gets Interesting. Eran Machlev Security Researcher Share We built the same three apps with five models on Base44 and ran Tenzai's AI hacker against...
research · vercel.com
DeepsecBench: evaluating model performance in finding cybersecurity vulnerabilities
Today we're releasing DeepsecBench, a benchmark that evaluates how well different models find security vulnerabilities in application code.
tool · projectdiscovery.io
Inside the benchmark: app architectures, walkthroughs of findings, and what each scanner actually caught
Part 2 of the vibe coding benchmark dissects three AI-built apps (healthcare, banking, insurance), detailing what Neo caught, what Claude Code got wrong, and what both missed on AI-generated code.
blog · xbow.com
How Attackers Are Using AI & What Defenders Must Do
Attackers are running AI driven attack chains from recon to exploitation in minutes. Here’s what actually changed, and why defenders need AI pentesting to keep pace.
blog · xbow.com
Grok 4.7 Is Different. So Is the Best Way to Use It.
XBOW tested Grok 4.7 on exploit crafting and agentic pentests: inside xAI's Build it improved substantially over 4.6, outside Build it slipped slightly—orchestration now matters as much as prompts.
Back