ADX Vision 2.0
BlackFog's endpoint-level AI security layer adding seven layers of prompt-injection protection and agentic AI governance.
Overview
BlackFog launched ADX Vision 2.0 on September 30, 2026, expanding its AI security product beyond Shadow AI discovery into a broader governance and control layer for enterprise generative and agentic AI. The release adds seven layers of prompt protection -- context switching protection, obfuscation protection, jailbreak detection, data exfiltration protection, dangerous prompt pattern detection, fuzzy keyword detection, and structural anomaly detection. ADX Vision 2.0 operates on the endpoint, before data reaches an AI service, giving organizations visibility, governance, and auditability over every AI interaction whether initiated by an employee or an AI agent. It is available now for Windows and macOS.
This is a sourced directory entry. Features and capabilities are reported in the linked sources; this entry does not document independent Aymorphic testing.
Key features
- Seven layers of prompt-injection and jailbreak protection
- Endpoint-level enforcement before data reaches any AI service
- Token management and AI governance controls
- Covers both human-initiated and agent-initiated AI interactions
- Builds on existing Shadow AI discovery and control capabilities
Use cases
- Blocking prompt-injection and jailbreak attempts before they reach an AI service
- Enterprise governance and audit trail of all AI interactions on managed endpoints
- Preventing data exfiltration via generative or agentic AI tools
- Shadow AI discovery across an organization's Windows/macOS fleet
Pricing
unknown -- no public per-seat pricing disclosed at launch.
Pricing reflects the source record and may change. Confirm current terms with the provider.
Dates and sources
- Released
- 30 Sept 2026
- Record updated
- 7 Oct 2026
- Record last checked
- 7 Oct 2026