AshAi exposes Ash read actions to language-model tool calls. The read tool accepts an aggregate result type (min, max, sum, avg) that builds an ad-hoc Ash.Query.Aggregate over a named field and returns its raw value.
Ash field policies redact forbidden fields on returned records (replacing them with %Ash.ForbiddenField{}), but that redaction does not apply to aggregate values. A tool caller could therefore read a field the calling actor's field policies forbid by requesting it as an aggregate; min/max in particular return an actual field value. This includes fields that are public? true but restricted per-actor by a field policy, such as sensitive PII. The tool's existing check only required the field to be public, which is a separate axis from per-actor field-policy authorization.
The fix authorizes the aggregated field against the resource's field policies, so aggregating over a field the actor may not see is refused or scoped to the rows where it is visible.
This issue affects ash_ai: from 0.1.0 before 1.0.3.
Ash field policies redact forbidden fields on returned records (replacing them with %Ash.ForbiddenField{}), but that redaction does not apply to aggregate values. A tool caller could therefore read a field the calling actor's field policies forbid by requesting it as an aggregate; min/max in particular return an actual field value. This includes fields that are public? true but restricted per-actor by a field policy, such as sensitive PII. The tool's existing check only required the field to be public, which is a separate axis from per-actor field-policy authorization.
The fix authorizes the aggregated field against the resource's field policies, so aggregating over a field the actor may not see is refused or scoped to the rows where it is visible.
This issue affects ash_ai: from 0.1.0 before 1.0.3.
Metrics
Affected Vendors & Products
Advisories
No advisories yet.
Fixes
Solution
No solution given by the vendor.
Workaround
No workaround given by the vendor.
References
History
Tue, 08 Sep 2026 16:45:00 +0000
| Type | Values Removed | Values Added |
|---|---|---|
| Description | AshAi exposes Ash read actions to language-model tool calls. The read tool accepts an aggregate result type (min, max, sum, avg) that builds an ad-hoc Ash.Query.Aggregate over a named field and returns its raw value. Ash field policies redact forbidden fields on returned records (replacing them with %Ash.ForbiddenField{}), but that redaction does not apply to aggregate values. A tool caller could therefore read a field the calling actor's field policies forbid by requesting it as an aggregate; min/max in particular return an actual field value. This includes fields that are public? true but restricted per-actor by a field policy, such as sensitive PII. The tool's existing check only required the field to be public, which is a separate axis from per-actor field-policy authorization. The fix authorizes the aggregated field against the resource's field policies, so aggregating over a field the actor may not see is refused or scoped to the rows where it is visible. This issue affects ash_ai: from 0.1.0 before 1.0.3. | |
| Title | AshAi aggregate tool can read field-policy-protected fields | |
| First Time appeared |
Ash-project
Ash-project ash Ai |
|
| Weaknesses | CWE-1220 | |
| CPEs | cpe:2.3:a:ash-project:ash_ai:*:*:*:*:*:*:*:* | |
| Vendors & Products |
Ash-project
Ash-project ash Ai |
|
| References |
|
|
| Metrics |
cvssV4_0
|
Projects
Sign in to view the affected projects.
Status: PUBLISHED
Assigner: EEF
Published:
Updated: 2026-09-08T17:33:57.604Z
Reserved: 2026-08-31T00:45:02.439Z
Link: CVE-2026-78230
No data.
Status : Received
Published: 2026-09-08T17:18:30.840
Modified: 2026-09-08T17:18:30.840
Link: CVE-2026-78230
No data.
OpenCVE Enrichment
Updated: 2026-09-08T17:30:05Z
Weaknesses