Skip to content
Threat Feed
Subscribe

Product

Azure AI Foundry

4 briefs RSS
medium advisory

Microsoft Azure AI Foundry: Responsible AI policy tampering

Adversaries with administrative access can weaken or delete Azure AI Foundry content filters and blocklists to bypass model guardrails and monitoring controls, effectively impairing defensive security instrumentation.

Azure AI Foundry azure defense-evasion cloud-security genai
1t
medium advisory

Microsoft Azure AI Foundry: Unauthorized API key and connection secret access

High-privilege Azure principals accessing Microsoft Foundry API keys or connection secrets are being monitored to prevent LLMjacking and unauthorized data pivoting.

Azure AI Services +1 credential-access cloud-security azure llmjacking
2t
high advisory

Detection of Credential Exposure in Azure AI Foundry Interactions

This detection monitors Azure API Management GatewayLogs for sensitive credential patterns accidentally included in LLM prompts or assistant replies, flagging potential data leakage through AI services.

Azure AI Foundry +1 azure-ai-foundry credential-access genai data-leakage cloud-security
1t
high advisory

CVE-2026-35435 Azure AI Foundry Elevation of Privilege Vulnerability

CVE-2026-35435 is an elevation of privilege vulnerability in Azure AI Foundry M365 that allows an unauthorized attacker to elevate privileges over a network due to improper access control in published agents.

Azure AI Foundry azure privilege-escalation cloud
2r 1t