GHSA-w676-mrp6-5fqq
LobeChat versions through 2.2.9 have a broken access control vulnerability in the retrieval-augmented-generation semantic search feature. Authenticated attackers can exploit missing user-identifier checks in the chunk model's semanticSearch method to access other users' data. This includes retrieving text content, file names, and metadata by supplying arbitrary victim file or knowledge-base identifiers. No patch information is currently available.
AI Analysis
Technical Summary
The vulnerability in LobeChat (up to version 2.2.9) involves broken access control within the semantic search functionality of the retrieval-augmented-generation feature. Specifically, the chunk model's semanticSearch method lacks proper user-identifier predicates, allowing authenticated attackers to supply arbitrary identifiers for files or knowledge bases belonging to other users. This flaw enables unauthorized access to sensitive data such as text content, file names, and metadata from other users' accounts.
Potential Impact
Authenticated attackers can bypass intended access restrictions to retrieve sensitive information belonging to other users, including text content, file names, and metadata. This compromises user data confidentiality and privacy within the affected LobeChat versions.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is released, restrict access to the affected semantic search functionality to trusted users only and monitor for suspicious activity involving knowledge-base or file identifier parameters.
GHSA-w676-mrp6-5fqq
Description
LobeChat versions through 2.2.9 have a broken access control vulnerability in the retrieval-augmented-generation semantic search feature. Authenticated attackers can exploit missing user-identifier checks in the chunk model's semanticSearch method to access other users' data. This includes retrieving text content, file names, and metadata by supplying arbitrary victim file or knowledge-base identifiers. No patch information is currently available.
CVSS v4.0
Affected software
Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
The vulnerability in LobeChat (up to version 2.2.9) involves broken access control within the semantic search functionality of the retrieval-augmented-generation feature. Specifically, the chunk model's semanticSearch method lacks proper user-identifier predicates, allowing authenticated attackers to supply arbitrary identifiers for files or knowledge bases belonging to other users. This flaw enables unauthorized access to sensitive data such as text content, file names, and metadata from other users' accounts.
Potential Impact
Authenticated attackers can bypass intended access restrictions to retrieve sensitive information belonging to other users, including text content, file names, and metadata. This compromises user data confidentiality and privacy within the affected LobeChat versions.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is released, restrict access to the affected semantic search functionality to trusted users only and monitor for suspicious activity involving knowledge-base or file identifier parameters.
Technical Details
- Gcve Source
- db.gcve.eu
- Osv Id
- GHSA-w676-mrp6-5fqq
- Osv Schema Version
- 1.4.0
- Aliases
- ["CVE-2026-59098"]
- Ecosystems
- []
- Database Specific Severity
- HIGH
- Cvss Version
- 4.0
Threat ID: 6a46eca627e9c7971943a3cb
Added to database: 07/02/2026, 22:56:38 UTC
Last enriched: 07/02/2026, 22:59:53 UTC
Last updated: 07/03/2026, 03:31:16 UTC
Views: 5
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.