CVE-2026-77956
Remote unauthenticated Elixir code injection in ash_ai prompt evaluation
Is CVE-2026-77956 being exploited?
Not confirmed. CVE-2026-77956 does not appear in CISA's Known Exploited Vulnerabilities catalog, which records only exploitation that has been observed and reported publicly. That is evidence of absence of a report, not evidence the flaw is unattacked. EPSS currently estimates a 0.19% probability of exploitation in the next 30 days.
How severe is CVE-2026-77956?
CVE-2026-77956 is rated High with a CVSS score of 8.9. Severity describes how bad exploitation would be, not how likely it is: pair it with exploitation evidence before deciding what to patch first.
Is there a patch for CVE-2026-77956?
Yes. A fix has been recorded for CVE-2026-77956. The vendor advisory is the authority on the exact fixed version — apply it from there rather than from a summary.
What does CVE-2026-77956 affect?
CVE-2026-77956 affects ash-project/ash_ai >=0.1.0, <1.0.0, AshAi.Actions.Prompt (EEx.eval_string). Confirm the exact affected versions against the vendor advisory before deciding you are exposed.
What should I do about CVE-2026-77956?
Upgrade to ash_ai 1.0.0+ or apply vendor patch; stop evaluating user-controlled prompts.
Exploitation status reflects CISA's KEV catalog as we last synced it. Check the catalog directly.
Remote unauthenticated attacker can execute arbitrary Elixir code via crafted prompt templates, enabling full server compromise.
Immediate action required
- affected>= 0.1.0 and < 1.0.0
- affected>= 4aab131d40a0bd5a8cf0b3c4eaaa59d49565f3d1 and < e9948254b5659c1143b73dc2f59f457931e64514
As published in the CVE Program record. A version outside these ranges is not a statement that it is unaffected — vendors sometimes understate a range, and distribution-backported builds carry upstream numbers that do not reflect what was patched into them.