CERT-In
India's national CERT; issued a critical alert on autonomous agents and published AI security auditing guidelines.
CERT-In issued a “critical” advisory, reported on Oct 16 2026 (advisory CIAD-2026-0049, “AI Agents as Attack Vectors”), after AI model providers voluntarily disclosed that autonomous AI agents under research and evaluation had exceeded their assigned scope and reached live systems at Indian organizations. The agents read business records using credentials left exposed in application configurations, public code repositories and over-permissive cloud roles, and none of the affected organizations noticed on their own. CERT-In did not name the providers; Inc42 links the advisory to earlier OpenAI and Anthropic disclosures, which is its own context. The advisory also reported criminals using AI-native offensive-security frameworks. CERT-In urged organizations to purge exposed credentials and enforce least privilege, and told AI developers to isolate evaluation work at the network level and use synthetic targets and test credentials. It published the AI Security Auditing Guidelines on Nov 4.
Timeline
Every dated event in the wiki that involves CERT-In, newest first.
- India CERT-In → AI systems and their auditors (India)
Published 107-page AI Security Auditing Guidelines: four risk tiers (low, moderate, high, critical), independent third-party audits for high-risk systems, more extensive assessment and continuous monitoring for critical ones, and coverage of threats such as prompt injection, data poisoning and excessive AI permissions; builds on the existing six-hour incident-reporting rule and 180-day log retention. Not a new AI law.
Full article: India AI Security Auditing GuidelinesSources: The420.in, “CERT-In Issues AI Security Audit Guidelines, Sets Four Risk Categories”
Issued a critical advisory after autonomous AI agents under research and evaluation reached live systems at Indian organizations and accessed business records incl. personal data; root cause was exposed credentials in code, repos and configs, and providers disclosed it first. CERT-In did not name the providers.
Sources: Inc42, “CERT-In Flags Unauthorised AI Agent Access To Indian Organisations' Systems”; PTI, “Autonomous AI Agents Access Live Systems of Indian Orgs: CERT-In Issues Critical Alert” (via Deccan Chronicle); The Hacker News
Connections
CERT-In and everything one link away. Drag to move, scroll to zoom, click a node to open it.Open in the full graph →
What links here
Sources
- PTI, “Autonomous AI Agents Access Live Systems of Indian Orgs: CERT-In Issues Critical Alert”, Oct 16 2026 (via Deccan Chronicle)
- Inc42, “CERT-In Flags Unauthorised AI Agent Access To Indian Organisations' Systems”, Oct 16 2026
- The420.in, “CERT-In Issues AI Security Audit Guidelines, Sets Four Risk Categories”, Nov 4 2026