CWE-918 Base Incompleto

Server-Side Request Forgery (SSRF)

Server-Side Request Forgery (SSRF) occurs when a web application fetches a remote resource based on user-controlled input, but fails to properly validate or restrict where those requests are sent.…

Definición

What is CWE-918?

Server-Side Request Forgery (SSRF) occurs when a web application fetches a remote resource based on user-controlled input, but fails to properly validate or restrict where those requests are sent. This allows an attacker to trick the server into making unauthorized connections to internal systems or external domains.
SSRF flaws are dangerous because they let attackers bypass firewalls and access sensitive internal infrastructure that should be unreachable from the outside. A common scenario involves an application that takes a URL parameter for fetching an image or importing data, but an attacker manipulates it to target internal admin panels, cloud metadata services, or other backend systems. This can lead to information disclosure, internal service enumeration, or even remote code execution if the server processes the malicious response. Preventing SSRF requires a defense-in-depth approach: implement allowlists for permitted domains and protocols, validate and sanitize all user input used in network requests, and avoid using raw URLs to fetch resources. Network-level controls like segregating internal services and enforcing outbound firewall rules are also critical. While SAST and DAST tools can detect the vulnerable pattern, Plexicus uses AI to analyze the specific context and suggest the precise code fix—such as implementing a secure URL validator—saving significant manual remediation time across your application portfolio.
Vulnerability Diagram CWE-918
Server-Side Request Forgery (SSRF) Attacker url=http://169.254.… Web app fetch(url) no host allowlist runs in VPC Cloud metadata 169.254.169.254/iam Internal services redis:6379, admin:8080 Server fetches attacker URL → reaches resources only the server can.
Impacto en el mundo real

Real-world CVEs caused by CWE-918

  • CVE-2024-3095

    SSRF in LLM application development framework because the URL retriever allows connections to local addresses using a crafted Location header

  • CVE-2023-32786

    Chain: LLM integration framework has prompt injection (CWE-1427) that allows an attacker to force the service to retrieve data from an arbitrary URL, essentially providing SSRF (CWE-918) and potentially injecting content into downstream tasks.

  • CVE-2021-26855

    Server Side Request Forgery (SSRF) in mail server, as exploited in the wild per CISA KEV.

  • CVE-2021-21973

    Server Side Request Forgery in cloud platform, as exploited in the wild per CISA KEV.

  • CVE-2016-4029

    Chain: incorrect validation of intended decimal-based IP address format (CWE-1286) enables parsing of octal or hexadecimal formats (CWE-1389), allowing bypass of an SSRF protection mechanism (CWE-918).

  • CVE-2002-1484

    Web server allows attackers to request a URL from another server, including other ports, which allows proxied scanning.

  • CVE-2004-2061

    CGI script accepts and retrieves incoming URLs.

  • CVE-2010-1637

    Web-based mail program allows internal network scanning using a modified POP3 port number.

Cómo lo explotan los atacantes

Ruta del atacante paso a paso

  1. 1

    Identifica una ruta de código que maneje entrada no confiable sin validación.

  2. 2

    Crea un payload que ejercite el comportamiento inseguro — inyección, traversal, overflow o abuso de lógica.

  3. 3

    Envía el payload a través de una solicitud normal y observa la reacción de la aplicación.

  4. 4

    Itera hasta que la respuesta filtre datos, ejecute código del atacante o escale privilegios.

Ejemplo de código vulnerable

Vulnerable pseudo

MITRE no ha publicado un ejemplo de código para esta CWE. El patrón siguiente es ilustrativo — consulta Recursos para referencias canónicas.

Vulnerable pseudo 
// Example pattern — see MITRE for the canonical references.
function handleRequest(input) {
  // Untrusted input flows directly into the sensitive sink.
  return executeUnsafe(input);
}
Ejemplo de código seguro

Secure pseudo

Seguro pseudo 
// Validate, sanitize, or use a safe API before reaching the sink.
function handleRequest(input) {
  const safe = validateAndEscape(input);
  return executeWithGuards(safe);
}
What changed: the unsafe sink is replaced (or the input is validated/escaped) so the same payload no longer triggers the weakness.
Lista de prevención

How to prevent CWE-918

  • Architecture Use safe-by-default frameworks and APIs that prevent the unsafe pattern from being expressible.
  • Implementation Validate input at trust boundaries; use allowlists, not denylists.
  • Implementation Apply the principle of least privilege to credentials, file paths, and runtime permissions.
  • Testing Cover this weakness in CI: SAST rules + targeted unit tests for the data flow.
  • Operation Monitor logs for the runtime signals listed in the next section.
Señales de detección

How to detect CWE-918

Automated Static Analysis High

Automated static analysis, commonly referred to as Static Application Security Testing (SAST), can find some instances of this weakness by analyzing source code (or binary/compiled code) without having to execute it. Typically, this is done by building a model of data flow and control flow, then searching for potentially-vulnerable patterns that connect "sources" (origins of input) with "sinks" (destinations where the data interacts with external components, a lower layer such as the OS, etc.)

Auto-corrección de Plexicus

Plexicus detecta automáticamente CWE-918 y abre un PR de corrección en menos de 60 segundos.

Codex Remedium escanea cada commit, identifica esta debilidad concreta y entrega un pull request listo para revisión con el parche. Sin tickets. Sin traspasos.

Solicitar demo Probar Plexicus gratis
Preguntas frecuentes

Frequently asked questions

¿Qué es CWE-918?

Server-Side Request Forgery (SSRF) occurs when a web application fetches a remote resource based on user-controlled input, but fails to properly validate or restrict where those requests are sent. This allows an attacker to trick the server into making unauthorized connections to internal systems or external domains.

¿Qué gravedad tiene CWE-918?

MITRE no ha publicado una calificación de probabilidad de explotación para esta debilidad. Trátala como de impacto medio hasta que tu modelo de amenazas demuestre lo contrario.

¿Qué lenguajes o plataformas se ven afectados por CWE-918?

MITRE lists the following affected platforms: AI/ML, Web Server.

¿Cómo puedo prevenir CWE-918?

Use safe-by-default frameworks, validate untrusted input at trust boundaries, and apply the principle of least privilege. Cover the data-flow signature in CI with SAST.

¿Cómo detecta y corrige Plexicus CWE-918?

El motor SAST de Plexicus detecta la firma de flujo de datos para CWE-918 en cada commit. Cuando hay coincidencia, nuestro agente Codex Remedium abre un PR de corrección con el código corregido, las pruebas y un resumen de una línea para el revisor.

¿Dónde puedo aprender más sobre CWE-918?

MITRE publica la definición canónica en https://cwe.mitre.org/data/definitions/918.html. También puedes consultar la documentación de OWASP y NIST para guías relacionadas.

Debilidades relacionadas

Weaknesses related to CWE-918

CWE-441 Padre

Unintended Proxy or Intermediary ('Confused Deputy')

A confused deputy vulnerability occurs when a system receives a request from a client and forwards it to an external destination without…

CWE-1021 Hermano

Improper Restriction of Rendered UI Layers or Frames

This vulnerability occurs when a web application fails to properly control whether its pages can be embedded within frames or UI layers…

Recursos

Further reading

Listo cuando tú lo estés

Deja de pagar por desarrollador.
Empieza a cerrar el bucle.

Plexicus es el ASPM nativo de IA que escanea, filtra, corrige, pentestea y explica — de forma autónoma. Desarrolladores ilimitados, repos ilimitados, acciones de IA de uso justo. Nivel gratuito real, €269/mo anual cuando estés listo.

Comenzar gratis Reservar una demo