VulnerabilityPublished 21 Jan 2024Updated 30 May 2025

CVE-2024-23730: The OpenAPI and ChatGPT plugin loaders in LlamaHub (aka llama-hub) before 0.0.67 allow attackers to

Source CVE Database V5

Not known to be exploited · CVSS 9.8 Critical : upgrade to 0.0.67 as a priority.

Data as of 26 Oct 2026, 13:47 UTC

CVSS 3.1 base score

9.8Critical

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

EPSS: 1.2% chance of exploitation in 30 days – higher than 68% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available – fixed in 0.0.67

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Attack Vector: Network
Attack Complexity: Low
Privileges Required: None
User Interaction: None
Scope: Unchanged
Confidentiality: High
Integrity: High
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: High: There is total loss of confidentiality, resulting in all resources within the impacted component being divulged to the attacker. Alternatively, access to only some restricted information is obtained, but the disclosed information presents a direct, serious impact.
Integrity: High: There is a total loss of integrity, or a complete loss of protection. For example, the attacker is able to modify any/all files protected by the impacted component. Alternatively, only some files can be modified, but malicious modification would present a direct, serious consequence to 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 21 Jan 2024
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 or the CVSS exploit maturity 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

Upgrade llama-hub to 0.0.67.

Affected software

Product	Affected	Fixed in
npmllama-hub`pkg:npm/llama-hub`Other threats	Affected <0.0.67	Fixed in 0.0.67

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

AI-suggested

Immediate upgrade: Organizations should upgrade LlamaHub to version 0.0.67 or later, where the vulnerability is patched by using safe_load for YAML parsing.
Input validation: Implement strict validation and sanitization of all YAML inputs, especially plugin descriptors and configuration files, to ensure they originate from trusted sources.
Network segmentation: Restrict network access to systems running LlamaHub plugin loaders to trusted internal networks or VPNs to reduce exposure.
Monitoring and detection: Deploy monitoring solutions to detect anomalous behavior indicative of code execution attempts, such as unexpected process spawning or network connections from AI service hosts.
Least privilege: Run LlamaHub services with the minimum necessary privileges to limit the impact of a potential compromise.
Incident response readiness: Prepare incident response plans specifically for AI platform compromises, including forensic capabilities to analyze YAML inputs and plugin activity.
Vendor engagement: Engage with LlamaHub maintainers or community for updates and security advisories to stay informed about further patches or mitigations.

Description

The OpenAPI and ChatGPT plugin loaders in LlamaHub (aka llama-hub) before 0.0.67 allow attackers to execute arbitrary code because safe_load is not used for YAML.

Impact

For European organizations, the impact of this vulnerability can be severe, especially for those leveraging AI and machine learning platforms that integrate LlamaHub for plugin management. Successful exploitation can lead to complete system takeover, data breaches, disruption of AI services, and potential lateral movement within corporate networks. Confidentiality is at risk due to arbitrary code execution allowing data exfiltration; integrity is compromised as attackers can alter or inject malicious code; availability can be disrupted by destructive payloads or ransomware. Organizations in sectors such as finance, healthcare, critical infrastructure, and technology, which increasingly adopt AI-driven solutions, may face operational disruptions and regulatory consequences under GDPR if personal data is exposed. The vulnerability’s network accessibility and lack of required privileges increase the likelihood of exploitation in exposed environments, making timely remediation critical.

References

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 8 Jul 2025, 17:14 UTC

Technical details

References

Community reviews

Related threats