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.
{
"cna_assigner": "EEF",
"cwe_ids": [
"CWE-1220"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/78xxx/CVE-2026-78230.json",
"unresolved_ranges": [
{
"extracted_events": [
{
"introduced": "0.1.0"
},
{
"fixed": "1.0.3"
},
{
"introduced": "2ba234b50946a3b8116190c8467f9f4dfa5edce7"
},
{
"fixed": "9c02de581625c342c9870a672830bff28c1d701e"
}
],
"source": "AFFECTED_FIELD"
},
{
"extracted_events": [
{
"introduced": "0.1.0"
},
{
"fixed": "1.0.3"
}
],
"source": "CPE_FIELD"
},
{
"extracted_events": [
{
"introduced": "0.1.0"
},
{
"fixed": "1.0.3"
}
],
"source": "DESCRIPTION"
}
]
}