CVE-2026-77956

HIGHPre-NVD 8.98.9—
EchelonGraph scoreMEDIUM confidence

This high-severity CVE scores 8.9 under a secondary CVSS source (NVD's own analysis pending). EPSS exploit probability: 0.2%, top 91% of all CVEs by exploit prediction. GitHub Security Advisory data not yet ingested — confidence will rise once GHSA publishes (typical lag: hours to days for open-source ecosystem CVEs; never for infrastructure-only CVEs).

Triggered by: NVD CVSS baseline
Sources: epss, secondary
Trending — 3 sources updated this weekElevated
8.9EG
EchelonGraph verdictPlan a fixSerious severity, but no confirmed exploitation yet.
  • High severity, but no confirmed exploitation yet
CISA-KEV: Not listedEPSS PROB: 0%CVSS: 8.9Exploit: Elevated riskExposed: 0

No vendor fix yet — apply a workaround or compensating control (WAF / firewall / segmentation) and watch for a patch.

Improper Control of Generation of Code (Code Injection) vulnerability in ash-project ash_ai allows a remote, unauthenticated client to execute arbitrary Elixir code.

AshAi.Actions.Prompt evaluates prompt content through EEx.eval_string/2. The documented prompt: fn input, context -> ... end form lets the prompt content be built from action arguments, so when a prompt action's text incorporates request data, that attacker-controlled text is compiled and run as an EEx template (Elixir source). Content such as <%= System.cmd(...) %> therefore executes on the server before any model request is made, requiring no authentication beyond reaching a prompt action. The fix stops evaluating function-supplied prompt content as EEx; only statically configured templates are evaluated.

This issue affects ash_ai: from 0.1.0 before 1.0.0.

CVSS v3
8.9
EG Score
8.9(medium)
EG Risk
56(Track*)
EG Risk 56/100SSVC: Track*

EG Risk is EchelonGraph's 0–100 priority score: it fuses intrinsic severity with real-world exploitation and automatability so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner. Distinct from the 0–10 EG Score (severity).

How it’s computed
Severity89% × 45%
Exploitation40% × 40%
Automatability0% × 15%
Action: Watch closely — could escalate to Attend.
EPSS PROB
0%
EPSS %ILE
9%
KEV
Not listed

Published

August 31, 2026

Last Modified

September 1, 2026

Advisory Details (4)

Auto-updated Aug 31, 2026
🔬 Proof of concept available. Patch available. Sources: github, github_commit.
generic

OSV - Open Source Vulnerabilities

https://osv.dev/vulnerability/EEF-CVE-2026-77956
github Patch Available🟡 PoC Available

Remote code execution in `AshAi.Actions.Prompt` in AshAi via EEx evaluation of prompt content built from user input · Advisory · ash-project/ash_ai · GitHub

https://github.com/ash-project/ash_ai/security/advisories/GHSA-2g59-hg7m-qc83
github_commit Patch Available

commit e9948254b565 (ash-project/ash_ai)

Patch available: ash-project/ash_ai v1.0.0 (contains commit e9948254b565)

https://github.com/ash-project/ash_ai/commit/e9948254b5659c1143b73dc2f59f457931e64514
generic

CVE-2026-77956

https://cna.erlef.org/cves/CVE-2026-77956.html

Affected Packages

(1 across 1 ecosystem)
Hex(1)
PackageVulnerable rangeFixed inDependents
ash_ai0.1.0 ... 0.8.2 (38 versions)1.0.0—

Weakness Classification(1)

MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.

Data Freshness Timeline

(refreshed 12× in last 7d / 12× in last 30d)

Each row is a source pipeline that fetched or updated this CVE on that date, with what changed. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. Most recent first.

  1. 2026-09-01 16:07 UTCEG score recompute
  2. 2026-09-01 13:54 UTCEPSS rescore
  3. 2026-09-01 04:40 UTCEPSS rescore
  4. 2026-09-01 04:40 UTCEPSS rescore
  5. 2026-09-01 04:14 UTCEG score recompute
  6. 2026-08-31 16:25 UTCEG score recompute
  7. 2026-08-31 16:16 UTCEG score recompute
  8. 2026-08-31 15:27 UTCEG score recompute▼ 1.10
  9. 2026-08-31 15:24 UTCMITRE cvelistV5CVSS v3 → 8.9 · CVSS v4 → 8.9 · severity → HIGH
  10. 2026-08-31 01:37 UTCEG score recompute
  11. 2026-08-31 01:05 UTCEG score recompute
  12. 2026-08-31 01:04 UTCMITRE cvelistV5first tracked

Related CVEs(same CWE)

Frequently asked(5)

What is CVE-2026-77956?
CVE-2026-77956 is a high vulnerability published on August 31, 2026. Improper Control of Generation of Code (Code Injection) vulnerability in ash-project ash_ai allows a remote, unauthenticated client to execute arbitrary Elixir code. AshAi.Actions.Prompt evaluates prompt content through EEx.eval_string/2. The documented prompt: fn input, context -> ... end form…
When was CVE-2026-77956 disclosed?
CVE-2026-77956 was first published in the National Vulnerability Database on August 31, 2026, with the most recent update on September 1, 2026. EchelonGraph re-ingests CVE updates from NVD on a 2-hour cycle, so this page reflects the latest published state.
Is CVE-2026-77956 actively exploited?
CVE-2026-77956 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0% probability of exploitation in the next 30 days, which ranks it in the top 90.7% of all scored CVEs.
What is the CVSS score of CVE-2026-77956?
CVE-2026-77956 has a CVSS v3 base score of 8.9 (NVD).
How do I remediate CVE-2026-77956?
Patch to the fixed version published by the affected vendor. Where vendor advisories exist for CVE-2026-77956, EchelonGraph cross-links them in the Vendor Advisories panel below — those typically contain the canonical remediation steps, fixed version numbers, and any vendor-specific mitigations.

Dependency Blast Radius

See which npm, PyPI, Go, and Maven packages are affected by CVE-2026-77956

Explore →

Is Your Infrastructure Affected by CVE-2026-77956?

EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.

Start Free Scan →Browse All CVEs