Science & Tech · Cybersecurity · 2 hrs ago
Ridge Security launches on-site AI penetration testing system
Ridge Security has announced RidgeOne, an AI-powered system for testing an organization’s computer security.
It is aimed at mid-sized organizations that may have limited security or AI resources.
RidgeOne runs tests inside the customer’s environment, so sensitive testing data is not sent to an external AI provider.
The system combines Ridge Security’s RidgeGen platform with an open-weight AI model running on NVIDIA DGX Spark, and is designed to avoid ongoing AI token costs.
In a test on OWASP Juice Shop, it found 32 verified issues in about 10 hours without operator involvement or external AI calls.
Nineteen findings were rated critical or high, and the system linked some weaknesses into a multi-step attack path.
Ridge Security says this can help security teams identify and prioritize fixes, but no further rollout or availability details are given.
Ridge Security announced RidgeOne, an on-site system for autonomous AI-powered penetration testing.
The system combines Ridge Security’s RidgeGen platform with an open-weight AI model running on NVIDIA DGX Spark.
It is designed to keep testing activity and sensitive data within customer environments without external AI calls.
In a test against OWASP Juice Shop, RidgeOne produced 32 verified findings, including 19 critical and high-severity findings, in about 10 hours.
- Who
- Ridge Security announced RidgeOne.
- What
- It is a self-contained system for autonomous AI-powered penetration testing and agentic red teaming.
- When
- The announcement was published on 2026-10-13.
- Where
- RidgeOne is designed to run within customer environments; the announcement’s location is not stated.
- Why
- It aims to make advanced security testing accessible while keeping data and infrastructure under customers’ control.
This story does not have two clearly opposing sides.
Ridge Security tested RidgeOne against OWASP Juice Shop and completed a full autonomous penetration test in approximately 10 hours.
Ridge Security’s announcement of RidgeOne was published.
- AI system
- Open-weight model running on NVIDIA DGX Spark
- Memory
- 128 GB of unified memory shared between the AI model and RidgeGen
- Test target
- OWASP Juice Shop
- Test results
- 32 verified findings, including 19 critical and high-severity findings
- Test duration
- Approximately 10 hours
What people are saying
We built RidgeOne to make autonomous security testing practical for organizations that want access to this technology while keeping control of their data, infrastructure and testing process.
RidgeOne gives organizations a practical way to bring AI-powered offensive security into their own environments while maintaining control over the data, the infrastructure and the testing process.
Sources
Related news
Cyberattack disrupts refrigeration at hundreds of French supermarkets
Cyberattack disrupts IT systems at three TFG London fashion brands
GitLab fixes maximum-severity flaw that could let attackers run server code
Ledger links CryptoBilis wallet implants to confirmed crypto thefts
Cyberattacks target refrigeration systems at more French supermarkets
Ahold Delhaize takes some systems offline after cyberattack
CISA adds five exploited software flaws amid China-linked espionage concerns
SAP fixes maximum-severity flaw in its Python Cloud SDK
Trellix launches on-premises AI tool for security investigations
Canadian cybersecurity executive arrested in ShinyHunters investigation
Only 25% of cybersecurity teams use agentic AI for defense
