VulnerabilityPublished 24 Sep 2025

CVE-2025-55178: Meta Platforms Llama Stack · OS Command Injection

Affects Meta Platforms Llama StackSource CVE Database V5

Not known to be exploited · CVSS 5.3 Medium.

Data as of 26 Oct 2026, 14:05 UTC

CVSS 3.1 base score

5.3Medium

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

EPSS: 0.5% chance of exploitation in 30 days – higher than 42% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.

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

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

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: Low: Modification of data is possible, but the attacker does not have control over the consequence of a modification, or the amount of modification is limited. The data modification does not have a direct, serious impact on the impacted component.
Availability: None: There is no impact to availability within the impacted component.

Definitions: FIRST CVSS v3.1 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 24 Sep 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 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

Affected software

Product	Affected	Fixed in
Meta Platforms, Inc Llama Stack	Affected =0.0.0	Fixed in–

AI-suggested

Immediate isolation or removal of vulnerable Llama Stack versions from production environments until a patch is available.
Implement strict input validation and sanitization at the application layer, especially for any parameters passed to resolve_ast_by_type or similar functions.
Employ network segmentation and firewall rules to restrict access to systems running Llama Stack, limiting exposure to trusted internal networks only.
Monitor logs and network traffic for unusual command execution patterns or unexpected process spawning indicative of exploitation attempts.
Use application-layer firewalls or runtime application self-protection (RASP) tools to detect and block injection attempts.
Engage with Meta Platforms for updates and patches, and subscribe to security advisories for timely remediation.
Conduct thorough code reviews and penetration testing focused on command injection vectors in AI stacks and related components.
Where feasible, deploy compensating controls such as containerization or sandboxing of Llama Stack processes to limit the impact of potential exploitation.

Description

Llama Stack prior to version v0.2.20 accepted unverified parameters in the resolve_ast_by_type function which could potentially allow for remote code execution.

Impact

For European organizations, the impact of CVE-2025-55178 could be severe, especially for those leveraging Meta's Llama Stack in AI, data processing, or other critical infrastructure. Successful exploitation could lead to unauthorized access to sensitive data, disruption of AI services, or use of compromised systems as pivot points for broader network attacks. Organizations in sectors such as finance, healthcare, telecommunications, and government, which increasingly adopt AI technologies, could face data breaches, operational downtime, and reputational damage. Additionally, the ability to execute arbitrary OS commands remotely increases the risk of malware deployment, ransomware attacks, or espionage activities. The lack of a patch means organizations must rely on immediate mitigations to reduce exposure. The threat is exacerbated if Llama Stack components are exposed to the internet or insufficiently segmented within internal networks. Given the strategic importance of AI technologies in Europe’s digital economy and regulatory frameworks like GDPR, exploitation could also lead to significant compliance and legal consequences.

CWE-78Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection') (opens in a new tab)
Base weaknessLikelihood of exploit: HighCWE Top 25 (2025): #9OWASP Top 10 A05:2025: Injection (opens in a new tab)
The product constructs all or part of an OS command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended OS command when it is sent to a downstream component.
Architecture and Design
If at all possible, use library calls rather than external processes to recreate the desired functionality.
Architecture and Design · Operation · Sandbox or Jail
Run the code in a "jail" or similar sandbox environment that enforces strict boundaries between the process and the operating system. This may effectively restrict which files can be accessed in a particular directory or which commands can be executed by the software.
Architecture and Design · Attack Surface Reduction
For any data that will be used to generate a command to be executed, keep as much of that data out of external control as possible. For example, in web applications, this may require storing the data locally in the session's state instead of sending it out to the client in a hidden form field.
OWASP Cheat Sheets
Injection Prevention (opens in a new tab)
Injection Prevention in Java (opens in a new tab)
OS Command Injection Defense (opens in a new tab)
Abuse Case (opens in a new tab)
Deserialization (opens in a new tab)
OWASP ASVS 4.0.3
V12.3.5 (opens in a new tab)
V5.3.8 (opens in a new tab)
V1.5.1 (opens in a new tab)
Attack patterns
Command Line Execution through SQL Injection (opens in a new tab)
Command Delimiters (opens in a new tab)
Exploiting Multiple Input Interpretation Layers (opens in a new tab)
Argument Injection (opens in a new tab)
OS Command Injection (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 24 Sep 2025, 18:41 UTC

WeaknessesCWE-78

Technical details

References

Community reviews

Related threats