# EEx template evaluation of prompt content in AshAi enables remote code execution

Advisory record · `GHSA-2g59-hg7m-qc83`

- **Identifiers:** `GHSA-2g59-hg7m-qc83` · `CVE-2026-77956` · `EEF-CVE-2026-77956`
- **State:** Confirmed
- **Severity:** CVSS 8.9 High
- **Critical:** No
- **Weakness (CWE):** [CWE-94](https://cwe.mitre.org/data/definitions/94.html)
- **Tags:** [Code injection](https://agentprime.io/advisories/tag/code-injection.md)
- **Published:** 31 Aug 2026
- **Updated:** 8 Sept 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 31 Aug 2026, 00:56 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `ash_ai` (Hex): affected `>=0.1.0, <1.0.0`; fixed in `1.0.0`

## Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

## Severity and exploitation

- 8.9 High, CVSS 4.0: `CVSS:4.0/AV:L/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H`, from CNA (EEF)

- **CISA KEV:** Not listed.
- **EPSS:** 0.0028, the 20th percentile, on 5 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

- 31 Oct 2026, 15:25 UTC: First seen by agentprime
- 31 Oct 2026, 15:25 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/EEF-CVE-2026-77956)

## Sources

- [GitHub Advisory Database: GHSA-2g59-hg7m-qc83](https://github.com/advisories/GHSA-2g59-hg7m-qc83)
- [OSV: GHSA-2g59-hg7m-qc83](https://osv.dev/vulnerability/GHSA-2g59-hg7m-qc83)
- <https://github.com/ash-project/ash_ai/security/advisories/GHSA-2g59-hg7m-qc83>
- <https://cna.erlef.org/cves/CVE-2026-77956.html>
- <https://github.com/ash-project/ash_ai/commit/e9948254b5659c1143b73dc2f59f457931e64514>
- <https://hex.pm/packages/ash_ai>

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.

## Check whether this affects you

A Match means an installed version is in the affected range above. Most don’t affect the app; agentprime hasn’t analysed this one yet.

- With the agentprime MCP server (<https://api.agentprime.io/mcp>), ask your agent to check the project: `check_lockfile` sends a lockfile, `check_packages` a list of installed packages, and both return the Matches and the upgrades that clear them. `get_advisory` returns this record. Setup: <https://agentprime.io/mcp.md>
- In a browser: <https://agentprime.io/check/> reads your lockfile in the browser, never uploading it.
- Whether it touches your code, with file and line: the Claude Code plugin, <https://agentprime.io/plugin.md>
- As JSON: <https://api.agentprime.io/v1/advisories/GHSA-2g59-hg7m-qc83>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-2g59-hg7m-qc83/>. Everything for agents: <https://agentprime.io/llms.txt>.