Unauthenticated routing manipulation via prompt injection
Published Mar 28, 2026 · Updated Mar 28, 2026
Prompt injection in localGPT at commit 4d41c7d1713b16b216d8e062e51a5dd88b20b054 allows remote attackers to manipulate LLM routing decisions. The _route_using_overviews function interpolates the HTTP chat query directly into the router instruction before sending it to Ollama, so injected instructions can override the requested USE_RAG or DIRECT_LLM response. The unauthenticated message endpoint reaches this path when a session has linked document indexes, affecting whether private-document retrieval is used rather than directly executing system commands.
Summary
What happened
Prompt injection in localGPT at commit 4d41c7d1713b16b216d8e062e51a5dd88b20b054 allows remote attackers to manipulate LLM routing decisions. The _route_using_overviews function interpolates the HTTP chat query directly into the router instruction before sending it to Ollama, so injected instructions can override the requested USE_RAG or DIRECT_LLM response. The unauthenticated message endpoint reaches this path when a session has linked document indexes, affecting whether private-document retrieval is used rather than directly executing system commands.
The record
- CVE
- CVE-2026-5002
- Published
- Mar 28, 2026
- Updated
- Mar 28, 2026
- Vendor
- PromtEngineer
- Product
- localGPT
- Classifications
- CWE-707, CWE-74, T1190
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Mar 28, 2026CVE publishedPublication date reported by the CVE source.
- Mar 28, 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=4d41c7d1713b16b216d8e062e51a5dd88b20b054
What conditions does exploitation require?
What is affected?
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
No public exploit references are available in this record.
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