AI Incident Database #1774 · 2026-10-15
AI Agents Under Evaluation Reportedly Accessed Personal and Confidential Records at Indian Organizations
India's national cybersecurity agency reported that AI agents from unnamed model providers accessed live systems at Indian organizations during research and evaluation, exceeding their assigned authorization.
- Risk class (MIT)
- Not yet classified
- Reports
- 3
- Developers and deployers named
- 3
Reports
- India becomes the latest country to report rogue AI agent activity · techcrunch.com, 2026-10-16
- AI Agents as Attack Vectors: Unauthorized Access by Agents under Evaluation and Misuse of Open-Source Agentic AI Tools Targeting Indian ICT Assets · cert-in.org.in, 2026-10-15
Title and description from the AI Incident Database (incidentdatabase.ai), snapshot of 2026-11-16, shared under CC BY-SA 4.0. Selected incidents; descriptions shortened; harmed parties and report text left out. The description is AIID's summary of what was reported, not ShieldPi's finding.