Unauthorized Gmail actions via untrusted email instructions
Published Jul 29, 2025 · Updated Aug 3, 2025
Indirect prompt injection in LangChain GmailToolkit 0.3.51 allows remote attackers to trigger Gmail actions through a crafted email. The demonstrated application passes attacker-controlled email content into the model, then executes resulting Gmail tool calls without an intent-alignment check. The supplier disputes that this is a LangChain flaw because the enforcement gap is in user-written agent code; the demonstration forwards email data rather than executing arbitrary code.
Summary
What happened
Indirect prompt injection in LangChain GmailToolkit 0.3.51 allows remote attackers to trigger Gmail actions through a crafted email. The demonstrated application passes attacker-controlled email content into the model, then executes resulting Gmail tool calls without an intent-alignment check. The supplier disputes that this is a LangChain flaw because the enforcement gap is in user-written agent code; the demonstration forwards email data rather than executing arbitrary code.
The record
- CVE
- CVE-2025-46059
- Published
- Jul 29, 2025
- Updated
- Aug 3, 2025
- Vendor
- Unknown vendor
- Product
- Unknown product
- Classifications
- CWE-94, T1567
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jul 29, 2025CVE publishedPublication date reported by the CVE source.
- Aug 3, 2025Record 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?
What conditions does exploitation require?
What is affected?
Affected products and versions are unavailable in this record.
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
- GmailToolkit malicious-email reproductionproof 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