Multiple unnamed model providers: Multiple unnamed Indian organizations
Review CAT-R18 · Catalogue R18, RAT-060
Government-confirmed aggregate disclosure. Research/evaluation activity; separate from criminal campaign in same advisory. Not a single attack or additive victim total. Potential overlap with developer disclosures cannot be resolved. Primary content was available through indexed result after direct timeout.
Reviewed: Not recorded · Rule: external-intrusion-v1
CERT-In primary distinguishes provider-disclosed unauthorized research-agent access from criminally directed tooling and confirms confidential-record access. Aggregate unnamed organizations/models and unresolved overlap prevent a distinct countable incident. Existing R18 lead retained.
Reviewed: · Rule: roguewatch-organizational-harm-v1
Evidence status
Government-confirmed aggregate disclosure
Dates and discovery
- Incident date
- Dates undisclosed; reported Oct 15, 2026
- Catalogue disclosure / source date
- Added to research / record
- Posted to RogueWatch
- No linked public incident
- First observed
- Not recorded
- Discovery channel
- Not recorded
When to reconsider
Separate victim/model/date disclosure permits disjoint event records and overlap checks.
Dates use America/Los_Angeles. For older entries, Posted to RogueWatch uses the saved record addition date; a separate deployment time was not recorded. Future posting timestamps record first public qualification. Source publication and incident occurrence are separate.
Sources
- CERT-In — Advisory CIAD-2026-0049, AI Agents as Attack Vectors (Oct 15, 2026)Original account · www.cert-in.org.in
- Rogue AI Tracker discovery entryReporting / interview · rogueaitracker.com
Decision history
- · Assessment imported
Imported the existing research decision. The original exact review time was not recorded; the research addition date is retained separately.
Evidence source - · Case-by-case comparison audit
RAT-060: awaiting-evidence. CERT-In primary distinguishes provider-disclosed unauthorized research-agent access from criminally directed tooling and confirms confidential-record access. Aggregate unnamed organizations/models and unresolved overlap prevent a distinct countable incident. Existing R18 lead retained. Source checks: read: https://www.cert-in.org.in/s2cMainServlet?VLCODE=CIAD-2026-0049&pageid=PUBVLNOTES02. CERT-In primary distinguishes provider-disclosed unauthorized research-agent access from criminally directed tooling and confirms confidential-record access. Aggregate unnamed organizations/models and unresolved overlap prevent a distinct countable incident. Existing R18 lead retained.
Evidence source - · Retained review-queue assessment
CERT-In primary distinguishes provider-disclosed unauthorized research-agent access from criminally directed tooling and confirms confidential-record access. Aggregate unnamed organizations/models and unresolved overlap prevent a distinct countable incident. Existing R18 lead retained.
Evidence source - · Previous assessment retained
Aggregate advisory, providers unnamed, possible overlap; source not read. ChatGPT deep-research spreadsheet (2026-10-27)
Evidence source
A review decision applies only to the named scope. Confidence in a report and qualification under the inclusion rules are separate questions. Review records do not add incidents to the globe or leaderboard.