How an AI-Based 'Pen Tester' Became a Top Bug Hunter on HackerOne
ID: ae431170-375b-568c-90aa-249afcae530e
STIX ID: report--ae431170-375b-568c-90aa-249afcae530e
Feed Name: Dark Reading
Threat Score
XBOW demonstrated an AI-driven autonomous penetration testing system that uses AI agents to find vulnerabilities and deterministic (non-LLM) validation — including a capture-the-flag style canary approach — to reduce false positives. The team scanned thousands of Docker Hub web applications, reported 174 vulnerabilities (22 confirmed CVEs) and produced a strong HackerOne track record, while highlighting the problem of LLM hallucinations producing many invalid bug reports.
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.