CVE-2024-12704VulnerabilityPublished 20 Mar 2025Updated 15 Oct 2025

CVE-2024-12704: run-llama/llama_index · Loop with Unreachable Exit Condition

Affects run-llama/llama_indexSource CVE Database V5

Not known to be exploited · CVSS 7.5 High.

Data as of 26 Oct 2026, 08:30 UTC

CVSS 3.0 base score

7.5High

How severe the flaw is on the 0–10 CVSS scale.

EPSS: 0.8% chance of exploitation in 30 days – higher than 57% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.

CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

Attack Vector: Network
Attack Complexity: Low
Privileges Required: None
User Interaction: None
Scope: Unchanged
Confidentiality: None
Integrity: None
Availability: High

Bold values are the worst case: easiest to exploit or largest impact.

Attack Vector: Network: The vulnerable component is bound to the network stack and the set of possible attackers extends beyond the other options listed, up to and including the entire Internet. Such a vulnerability is often termed 'remotely exploitable' and can be thought of as an attack being exploitable at the protocol level one or more network hops away (e.g., across one or more routers).
Attack Complexity: Low: Specialized access conditions or extenuating circumstances do not exist. An attacker can expect repeatable success against the vulnerable component.
Privileges Required: None: The attacker is unauthorized prior to attack, and therefore does not require any access to settings or files to carry out an attack.
User Interaction: None: The vulnerable system can be exploited without any interaction from any user.
Scope: Unchanged: An exploited vulnerability can only affect resources managed by the same security authority. In this case, the vulnerable component and the impacted component are either the same, or both are managed by the same security authority.
Confidentiality: None: There is no loss of confidentiality within the impacted component.
Integrity: None: There is no loss of integrity within the impacted component.
Availability: High: There is total loss of availability, resulting in the attacker being able to fully deny access to resources in the impacted component; this loss is either sustained (while the attacker continues to deliver the attack) or persistent (the condition persists even after the attack has completed). Alternatively, the attacker has the ability to deny some availability, but the loss of availability presents a direct, serious consequence to the impacted component (e.g., the attacker cannot disrupt existing connections, but can prevent new connections; the attacker can repeatedly exploit a vulnerability that, in each instance of a successful attack, leaks a only small amount of memory, but after repeated exploitation causes a service to become completely unavailable).

Definitions: FIRST CVSS v3.1 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 20 Mar 2025
Detectable: no evidence on record.
No public nuclei template indexed
Weaponised: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 26 Oct 2026.

Disclosed: The CVE record is public on cve.org. Its publication is t = 0.
Detectable: A public nuclei template can find exposed instances, for defenders and attackers alike.
Weaponised: Public exploit code exists in Metasploit or Exploit-DB, or CISA SSVC reports a public proof of concept.
Exploited in the wild: CISA KEV lists it, CISA SSVC rates exploitation active, or a source reports attacks.
Observed by OffSeq Mirage: OffSeq Mirage honeypot sensors recorded attack traffic for this CVE, or found exposed hosts without attack traffic.

Moments are spaced evenly, not to scale; a dashed line marks a gap of six months or more. Deltas count from t = 0. Sources that give only a date (CISA KEV, Exploit-DB, or a time of exactly 00:00Z) read “same day” rather than hours. Metasploit modules carry the flaw’s disclosure date, not their release date, and nuclei templates carry no date, so both appear above but not on the timeline.

What to do

Affected software

Product	Affected	Fixed in
GitHubrun-llama/llama_index`pkg:github/run-llama/llama_index`Other threats	Affected =0.12.5	Fixed in–

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

To mitigate this vulnerability, organizations should implement strict input validation to ensure only correctly typed inputs are passed to the LangChainLLM class, preventing thread failures triggered by malformed inputs. Developers should enhance the run-llama/llama_index codebase by adding robust exception handling around the thread execution and the get_response_gen method to detect and gracefully handle abnormal thread termination, thereby avoiding infinite loops. Monitoring and alerting on abnormal CPU or thread usage in systems running this software can provide early detection of exploitation attempts. Until an official patch is released, consider isolating the affected components within containerized or sandboxed environments to limit resource impact. Additionally, applying runtime protections such as watchdog timers or process supervisors can help terminate hung processes automatically. Engage with the vendor or open-source maintainers to track patch availability and apply updates promptly once released. Finally, conduct security testing and fuzzing on inputs to identify and remediate similar issues proactively.

Description

A vulnerability in the LangChainLLM class of the run-llama/llama_index repository, version v0.12.5, allows for a Denial of Service (DoS) attack. The stream_complete method executes the llm using a thread and retrieves the result via the get_response_gen method of the StreamingGeneratorCallbackHandler class. If the thread terminates abnormally before the _llm.predict is executed, there is no exception handling for this case, leading to an infinite loop in the get_response_gen function. This can be triggered by providing an input of an incorrect type, causing the thread to terminate and the process to continue running indefinitely.

Impact

For European organizations, this vulnerability poses a significant risk of service disruption in AI-driven applications that utilize the run-llama/llama_index framework. A successful exploit can cause indefinite resource consumption leading to Denial of Service, impacting availability of critical AI services such as chatbots, automated customer support, or data processing pipelines. This can degrade user experience, interrupt business operations, and potentially cause cascading failures if dependent systems rely on these AI components. Given the increasing adoption of AI technologies across sectors like finance, healthcare, and manufacturing in Europe, the impact could be widespread. Additionally, organizations with compliance requirements around service availability and operational resilience (e.g., under GDPR or NIS Directive) may face regulatory scrutiny if disruptions occur. While confidentiality and integrity are not directly affected, the availability impact alone is substantial, especially for real-time or high-availability AI services.

References

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 15 Oct 2025, 13:23 UTC

WeaknessesCWE-835

Technical details

References

Community reviews

Related threats