Skip to content
NewA calmer, faster ZeroHour
Researchmedium

$20 per zero-day is already the WordPress plugin reality

Help Net Securityby @helpnetsecurity ()3 min read4
AI summary · glm-5.3-flashSummaries by Vani AI

TrendAI and CHT Security used an AI pipeline to find over 300 verified WordPress plugin zero-days at roughly $20 per vulnerability.

A pipeline built in three days by TrendAI and CHT Security, presented at Ekoparty Miami, paired AI-driven static analysis with automated Docker provisioning and Chrome DevTools MCP dynamic verification to surface more than 300 critical zero-days in WordPress plugins within 72 hours. The run consumed about 222 million tokens across 95 tasks, averaging roughly $20 per verified vulnerability, with findings including pre-auth RCE, SQL injection, privilege escalation, SSRF, and an AI-assembled downgrade attack chain. Dynamic verification eliminated over 80% of false positives, but manual review at 30-60 minutes per finding remains the bottleneck, straining ZDI and NIST triage backlogs.

Key facts
  • Agent autonomously chained a downgrade flaw with vulnerabilities in an older plugin version
  • One pre-auth RCE was found in a plugin with over 1,000 GitHub stars
  • Disclosure triage at 30-60 minutes per finding is the primary bottleneck
  • Researchers expect rising zero-day abuse as attackers run similar pipelines
Analyze this story with Vani AIImpact, who is affected and what defenders should do, in a new chat

From the original article

3 min read at helpnetsecurity.com

Vulnerability researchers have spent the past year arguing about whether AI agents can find real bugs at scale or whether they mostly generate noise. A pipeline built in three days by researchers from TrendAI and CHT Security supplies an answer, along with a price tag that the security industry will have to reckon with.

Help Net Security

By @helpnetsecurity · helpnetsecurity.com

Read the full article at Help Net Security

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.