AI Security Incident
Evidence indicates that Microsoft Copilot is affected by a security issue.
DEVELOPING
What Happened
Evidence indicates that Microsoft Copilot is affected by a security issue.
Why This Matters
Current evidence identifies a security issue involving Microsoft Copilot, but does not yet support a more specific impact claim.
Recommended Action
No confirmed vendor remediation is available in the current evidence. Confirm whether Microsoft Copilot is present in your environment and review the affected configuration.
Exposure
Jun 11, 2025 05:30
Jan 15, 2026 05:30
Exploitation status: UNKNOWN
Primary entities:
Authoritative Intelligence
Timeline
-
Incident first seen
Jun 11, 2025 05:30BugSkan first recorded this incident.
-
Critical flaw in Microsoft Copilot could have allowed zero-click attack - Cybersecurity Dive
Jun 11, 2025 05:30cybersecuritydive.com · Vulnerability
-
Zero-Click AI Vulnerability Exposes Microsoft 365 Copilot Data Without User Interaction - The Hacker News
Jun 12, 2025 05:30thehackernews.com · Vulnerability
-
Microsoft 365 Copilot: New Zero-Click AI Vulnerability Allows Corporate Data Theft - Infosecurity Magazine
Jun 13, 2025 05:30infosecurity-magazine.com · Vulnerability
-
Preventing Zero-Click AI Threats: Insights from EchoLeak - www.trendmicro.com
Jul 15, 2025 05:30trendmicro.com · Data Leak
-
ServiceNow patches critical AI platform flaw that could allow user impersonation - CyberScoop
Jan 13, 2026 05:30cyberscoop.com · Vulnerability
-
ServiceNow Patches Critical AI Platform Flaw Allowing Unauthenticated User Impersonation - The Hacker News
Jan 13, 2026 05:30thehackernews.com · Vulnerability
-
ServiceNow patches critical AI Platform vulnerability enabling user impersonation - SC Media
Jan 15, 2026 05:30scworld.com · Vulnerability
-
Researchers Reveal Reprompt Attack Allowing Single-Click Data Exfiltration From Microsoft Copilot - The Hacker News
Jan 15, 2026 05:30thehackernews.com · Vulnerability
-
Latest observed development
Jan 15, 2026 05:30Most recent source or update associated with this incident.
-
Material change
Aug 18, 2026 14:07severity 8.2 -> 6.7
Sources
cybersecuritydive.com · Jun 11, 2025 05:30
A critical zero-click vulnerability, dubbed "EchoLeak" and identified as CVE-2025-32711, was discovered in Microsoft Copilot. This flaw leveraged an "LLM scope violation" to allow remote attackers to exfiltrate sensitive data from Microsoft 365 services without any user interaction.
Open publisher sourcethehackernews.com · Jun 12, 2025 05:30
A critical zero-click AI vulnerability, identified as EchoLeak (CVE-2025-32711, CVSS 9.3), allowed for unauthorized data exfiltration from Microsoft 365 Copilot without user interaction. This flaw leveraged an LLM Scope Violation and indirect prompt injection within markdown content to trick the AI's Retrieval-Augmented Generation (RAG) engine into leaking sensitive contextual data.
Open publisher sourceinfosecurity-magazine.com · Jun 13, 2025 05:30
Researchers have uncovered "EchoLeak," a critical zero-click vulnerability in Microsoft 365 Copilot that exploits design flaws inherent to Retrieval Augmented Generation (RAG) applications. This flaw, leveraging an "LLM Scope Violation" technique, allows for the automatic exfiltration of sensitive corporate data from the LLM's context without requiring user interaction.
Open publisher sourcetrendmicro.com · Jul 15, 2025 05:30
EchoLeak (CVE-2025-32711) is a zero-click AI vulnerability that exploits Microsoft 365 Copilot's retrieval-augmented generation (RAG) capabilities. It leverages invisible prompt injections embedded in contextual data to silently exfiltrate sensitive information without user interaction.
Open publisher sourcecyberscoop.com · Jan 13, 2026 05:30
A critical vulnerability, CVE-2025-12420 (CVSS 9.3), was patched in ServiceNow's AI platform, allowing unauthenticated user impersonation and unauthorized actions. Furthermore, researchers identified that default configurations in Now Assist AI Agents could facilitate "second-order prompt injection" attacks, enabling low-privileged users to exploit inter-agent communication for data access and privilege escalation.
Open publisher sourcethehackernews.com · Jan 13, 2026 05:30
ServiceNow patched CVE-2025-12420, codenamed BodySnatcher, a critical vulnerability (CVSS 9.3) in its AI Platform that allowed unauthenticated user impersonation. This flaw enabled attackers to bypass MFA/SSO by chaining a hardcoded secret with email-based account linking, facilitating arbitrary actions and potential privilege escalation.
Open publisher sourcescworld.com · Jan 15, 2026 05:30
ServiceNow has patched CVE-2025-12420, dubbed "BodySnatcher," a critical AI Platform vulnerability with a CVSS score of 9.3. This flaw allowed unauthenticated attackers to impersonate users and execute arbitrary actions within affected Now Assist AI Agents and Virtual Agent APIs.
Open publisher sourcethehackernews.com · Jan 15, 2026 05:30
Researchers unveiled a "Reprompt" attack method enabling single-click data exfiltration from Microsoft Copilot by exploiting the "q" URL parameter for indirect prompt injection. This attack bypasses enterprise security controls and guardrails, facilitating continuous, hidden data exfiltration via attacker-controlled servers without further user interaction.
Open publisher sourceWatchlist Match
Create an account to see which incidents overlap with the technologies you monitor.