Data exfiltration via unsanitized form prompt
Published Jan 22, 2026 · Updated Jan 22, 2026
Indirect prompt injection in Microsoft Copilot Studio allows remote attackers to read sensitive data through a crafted SharePoint form submission. Copilot Studio concatenates the form's untrusted Comments value with agent system instructions, allowing injected text to override the intended prompt. The agent must process a public form and have access to connected SharePoint Lists and an external-email action; the demonstrated consequence is data exfiltration.
Summary
What happened
Indirect prompt injection in Microsoft Copilot Studio allows remote attackers to read sensitive data through a crafted SharePoint form submission. Copilot Studio concatenates the form's untrusted Comments value with agent system instructions, allowing injected text to override the intended prompt. The agent must process a public form and have access to connected SharePoint Lists and an external-email action; the demonstrated consequence is data exfiltration.
The record
- CVE
- CVE-2026-21520
- Published
- Jan 22, 2026
- Updated
- Jan 22, 2026
- Vendor
- Microsoft
- Product
- Microsoft Copilot Studio
- Classifications
- CWE-77, T1190
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jan 22, 2026CVE publishedPublication date reported by the CVE source.
- Jan 22, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=-
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- ShareLeak demonstrationproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo