SOC status:Duty analyst on shift

UK Cyber Defence
VulnerabilityDeferred

CVE-2026-78230

AshAi exposes Ash read actions to language-model tool calls.

MEDIUM 6.0EPSS 0.25%

Does this matter?

Lower severity and a low EPSS score (0.25%). Track it; it rarely justifies an emergency change on its own.

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.

CVSS 4.0
6.0 MEDIUMCVSS: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/M
EPSS
0.25% probability · 16th percentile
CISA KEV
Not listed
Weakness
CWE-1220
Source
6b3ad84c-e1a6-4bf7-a703-f496b71e49db

Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.