Protected-data disclosure via concatenated SQLite filter keys
Published Oct 26, 2025 · Updated Oct 26, 2025
SQL injection in LangGraph's SQLite store 2.0.10 and earlier allows local users to read protected documents via crafted filter keys. The SqliteStore filter builders interpolate each filter key into json_extract WHERE expressions without validating or binding it as data. A low-privileged caller who can submit a filter to an application using this store can alter query structure, bypass application filters, and retrieve private records; LangSmith deployments use a different checkpointer and are unaffected.
Summary
What happened
SQL injection in LangGraph's SQLite store 2.0.10 and earlier allows local users to read protected documents via crafted filter keys. The SqliteStore filter builders interpolate each filter key into json_extract WHERE expressions without validating or binding it as data. A low-privileged caller who can submit a filter to an application using this store can alter query structure, bypass application filters, and retrieve private records; LangSmith deployments use a different checkpointer and are unaffected.
The record
- CVE
- CVE-2025-8709
- Published
- Oct 26, 2025
- Updated
- Oct 26, 2025
- Vendor
- LangChain
- Product
- LangChain
- Classifications
- CWE-89
- Attack vector
- local
- Privileges
- authenticated
Timeline
How it unfolded
- Oct 26, 2025CVE publishedPublication date reported by the CVE source.
- Oct 26, 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?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=unspecified <=latest
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
- SQLite filter-key SQL injection PoCproof 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