As cited
Copy frozen at (site build).
ai security
Google’s AI security agents found 100+ critical software vulnerabilities in just two days
Google's Mandiant disclosed the Agentic Vulnerability Discovery Harness (AVDH), an internal AI tool that chains multiple agents together to identify vulnerabilities in source code. During a two-day live investigation of stolen corporate repositories, AVDH discovered over 100 verified high-severity flaws. The tool has been operational for ten months and has scanned tens of millions of lines of code.
Why it matters: Security teams and development organizations should consider how AI-driven vulnerability discovery could accelerate code review workflows and catch critical flaws at scale in their own environments.
- Source published
- First seen by Cybersecurity Tracker
Source attribution
Correction
Correction recorded as of .
ai security
Google’s AI security agents found 100+ critical software vulnerabilities in just two days
No summary had been written when this copy was frozen.
- First seen by Cybersecurity Tracker
Source attribution
Correction
Correction recorded as of .
ai security
Google’s AI security agents found 100+ critical software vulnerabilities in just two days
Google's Mandiant disclosed an internal tool called the Agentic Vulnerability Discovery Harness (AVDH) that uses chains of artificial intelligence (AI) agents to identify vulnerabilities in source code. During a two-day investigation into stolen corporate repositories, the tool discovered over 100 verified high-severity flaws. AVDH has operated within Mandiant for ten months and scanned tens of millions of lines of code.
Why it matters: Security teams and code repository owners should understand that AI-powered vulnerability scanning can rapidly surface critical flaws at scale, informing decisions about code review processes and threat hunting prioritization.
- Source published
- First seen by Cybersecurity Tracker
Source attribution
Correction
Correction recorded as of .
ai security
Google’s AI security agents found 100+ critical software vulnerabilities in just two days
Google's Mandiant disclosed an internal tool called the Agentic Vulnerability Discovery Harness (AVDH) that uses chains of artificial intelligence (AI) agents to identify vulnerabilities in source code. During a two-day investigation into stolen corporate repositories, the tool discovered over 100 verified high-severity flaws. AVDH has operated within Mandiant for ten months and scanned tens of millions of lines of code.
Why it matters: Security teams and code repository owners should understand that AI-powered vulnerability scanning can rapidly surface critical flaws at scale, informing decisions about code review processes and threat hunting prioritization.
- Source published
- First seen by Cybersecurity Tracker