AshAi exposes Ash read actions to language-model tool calls. The read tool accepts an aggregate result type (min, max, sum, avg) that…
EEF·CWE-1220·Published 2026-09-08
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.
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.
## Summary 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. ## Configurations Reachable only when an application exposes an AshAi read tool over a resource whose field policies restrict a field that the calling actor can still name as an aggregate (for example a `public? true` but field-policy-protected attribute).
| Version | Type | Source | Base | Exp | Impact | Vector |
|---|---|---|---|---|---|---|
| 4.0 | Primary | cve.org | 6.0 | — | — | CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N |
| 4.0 | Secondary | NVD | 6.0 | — | — | CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:H/VI:N/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 |
| 4.0 | Secondary | ENISA EUVD | 6.0 | — | — | CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N |