Observability for AI Systems: Strengthening visibility for proactive risk detection
2026-03-18T20:52:21Z•0af0d5947b8bca782af46f3f5ef88787d52a73a9766b31d32e3bc660a0a973c6
AI securityContagious InterviewCoral SleetFlexibleFerretIOCsJasper SleetMicrosoft PurviewMicrosoft TeamsOtterCookieSEO poisoningStorm-2561credential theftdata governanceemail securityfake VPN clientsmitigationsobservabilityprompt abuseprompt injectionsocial engineeringsupply chainthreat actortrojanvoice phishing
What happened
Microsoft Security Blog collection (March 2026) covering AI security, governance, and active threat reports. Key topics: improving observability for AI systems and defenses against prompt injection/prompt abuse; new Microsoft Purview innovations for secure AI data governance; case study of a Microsoft Teams voice‑phishing (identity‑led) intrusion; Storm‑2561’s SEO‑poisoning campaign (active since 2025) distributing signed trojans via fake VPN clients to steal VPN credentials; the Contagious Interview campaign delivering OtterCookie and FlexibleFerret backdoors via fake developer interviews to盗
Why it matters
A reviewed impact interpretation has not been published for this record.
Evidence and limitations
- Source ID
- microsoft_security_blog
- Record identifier
- 0af0d5947b8bca782af46f3f5ef88787d52a73a9766b31d32e3bc660a0a973c6
- Enrichment time
- 2026-03-18T20:52:21Z
- AI-assisted enrichment
- Yes
This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.