Application hang via unbounded response loop
Published Mar 20, 2025 · Updated Oct 15, 2025
Denial of service in LlamaIndex before 0.12.6 allows remote attackers to hang a consuming application with an invalid input type. LangChainLLM.stream_complete starts a prediction thread, but get_response_gen loops without a timeout when that thread exits before setting its completion event. Exploitation requires an application to pass attacker-controlled input into this streaming path; the resulting loop consumes resources and leaves that application unresponsive.
Summary
What happened
Denial of service in LlamaIndex before 0.12.6 allows remote attackers to hang a consuming application with an invalid input type. LangChainLLM.stream_complete starts a prediction thread, but get_response_gen loops without a timeout when that thread exits before setting its completion event. Exploitation requires an application to pass attacker-controlled input into this streaming path; the resulting loop consumes resources and leaves that application unresponsive.
The record
- CVE
- CVE-2024-12704
- Published
- Mar 20, 2025
- Updated
- Oct 15, 2025
- Vendor
- LlamaIndex
- Product
- LlamaIndex
- Classifications
- CWE-835, T1499.004
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Mar 20, 2025CVE publishedPublication date reported by the CVE source.
- Oct 15, 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 <0.12.6
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
- Huntr proof-of-concept bountyproof 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