Microsoft warns prompt injection can hijack enterprise AI agents
Project Perception will discover agents, isolate runtimes and apply task-scoped permissions outside the model.
52
Product
Microsoft Execution Container
- Mentions · 7d2
- Mentions · 30d2
- All mentions2
- First seenOct 19, 2026
- Last mentioned5d ago
Timeline
2 articles · newest firstMicrosoft extends Project Perception to secure AI agents as insiders
Discovery grows to 60 local agent types, and Entra Agent ID can cover agents found only through sensors.
52
Appears with
- Microsoftvendor · 2
- Microsoft Entra Agent IDproduct · 2
- Project Perceptionproduct · 2
- GitHub Copilotproduct · 1
- Claude Codeproduct · 1
- OpenAI Codexproduct · 1
- Microsoft Agent 365product · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.