Security
Headlines
HeadlinesLatestCVEs

Headline

GHSA-p6jq-8vc4-79f6: Nuxt has Client-Side Path Traversal in Nuxt Island Payload Revival

Summary

A client-side path traversal vulnerability in Nuxt’s Island payload revival mechanism allowed attackers to manipulate client-side requests to different endpoints within the same application domain when specific prerendering conditions are met.

Technical Details

The vulnerability occurs in the client-side payload revival process (revive-payload.client.ts) where Nuxt Islands are automatically fetched when encountering serialized __nuxt_island objects. The issue affects the following flow:

  1. During prerendering, if an API endpoint returns user-controlled data containing a crafted __nuxt_island object
  2. This data gets serialized with devalue.stringify and stored in the prerendered page
  3. When a client navigates to the prerendered page, devalue.parse deserializes the payload
  4. The Island reviver attempts to fetch /__nuxt_island/${key}.json where key could contain path traversal sequences

Prerequisites for Exploitation

This vulnerability requires all of the following conditions:

  1. Prerendered pages: The application must use Nuxt’s prerendering feature (nitro.prerender)
  2. Attacker-controlled API responses: The attacker must be able to control the response content of an API endpoint that is called during prerendering via useFetch, useAsyncData, or similar composables
  3. Client-side navigation: A user must navigate to the prerendered page (not during initial SSR hydration)

Attack Scenario

// Malicious API response during prerendering
{
  "__nuxt_island": {
    "key": "../../../../internal/service",
    "params": { "action": "probe" }
  }
}

This could cause the client to make requests to /__nuxt_island/../../../../internal/service.json if path traversal is not properly handled by the server.

Impact Assessment

  • Limited Impact: The vulnerability has a low severity due to the highly specific prerequisites
  • No Direct Data Exfiltration: The vulnerability does not directly expose sensitive data
  • Client-Side Only: Requests originate from the client, not the server

Mitigation

Action Required:

  • Update to Nuxt 3.19.0+ or 4.1.0+ immediately
  • Review any prerendered pages that fetch external or user-controlled data

Temporary Workarounds (if immediate update is not possible):

  1. Disable prerendering for pages that fetch user-controlled data
  2. Implement strict input validation on API endpoints used during prerendering
  3. Use allowlists for API response structures during prerendering

Fix Details

The fix implemented validation for Island keys in revive-payload.server.ts:

  • Island keys must match the pattern /^[a-z][a-z\d-]*_[a-z\d]+$/i
  • Maximum length of 100 characters
  • Prevents path traversal and special characters
ghsa
#vulnerability#js#git#java#perl

Summary

A client-side path traversal vulnerability in Nuxt’s Island payload revival mechanism allowed attackers to manipulate client-side requests to different endpoints within the same application domain when specific prerendering conditions are met.

Technical Details

The vulnerability occurs in the client-side payload revival process (revive-payload.client.ts) where Nuxt Islands are automatically fetched when encountering serialized __nuxt_island objects. The issue affects the following flow:

  1. During prerendering, if an API endpoint returns user-controlled data containing a crafted __nuxt_island object
  2. This data gets serialized with devalue.stringify and stored in the prerendered page
  3. When a client navigates to the prerendered page, devalue.parse deserializes the payload
  4. The Island reviver attempts to fetch /__nuxt_island/${key}.json where key could contain path traversal sequences

Prerequisites for Exploitation

This vulnerability requires all of the following conditions:

  1. Prerendered pages: The application must use Nuxt’s prerendering feature (nitro.prerender)
  2. Attacker-controlled API responses: The attacker must be able to control the response content of an API endpoint that is called during prerendering via useFetch, useAsyncData, or similar composables
  3. Client-side navigation: A user must navigate to the prerendered page (not during initial SSR hydration)

Attack Scenario

// Malicious API response during prerendering { "__nuxt_island": { "key": "…/…/…/…/internal/service", "params": { "action": “probe” } } }

This could cause the client to make requests to /__nuxt_island/…/…/…/…/internal/service.json if path traversal is not properly handled by the server.

Impact Assessment

  • Limited Impact: The vulnerability has a low severity due to the highly specific prerequisites
  • No Direct Data Exfiltration: The vulnerability does not directly expose sensitive data
  • Client-Side Only: Requests originate from the client, not the server

Mitigation

Action Required:

  • Update to Nuxt 3.19.0+ or 4.1.0+ immediately
  • Review any prerendered pages that fetch external or user-controlled data

Temporary Workarounds (if immediate update is not possible):

  1. Disable prerendering for pages that fetch user-controlled data
  2. Implement strict input validation on API endpoints used during prerendering
  3. Use allowlists for API response structures during prerendering

Fix Details

The fix implemented validation for Island keys in revive-payload.server.ts:

  • Island keys must match the pattern /^[a-z][a-z\d-]*_[a-z\d]+$/i
  • Maximum length of 100 characters
  • Prevents path traversal and special characters

References

  • GHSA-p6jq-8vc4-79f6
  • nuxt/nuxt@2566d20

ghsa: Latest News

GHSA-393w-9x6h-8gc7: Pingora update for MadeYouReset HTTP/2 vulnerability