# ouroboros-ai: Incomplete fix of CVE-2026-47211: untrusted project .env can still reach RCE via omitted execution-routing keys

Advisory record · `GHSA-jv2h-4p9v-wf5w`

- **Identifiers:** `GHSA-jv2h-4p9v-wf5w` · `CVE-2026-66065`
- **State:** Confirmed
- **Severity:** CVSS 8.4 High
- **Critical:** No
- **Weakness (CWE):** [CWE-15](https://cwe.mitre.org/data/definitions/15.html) · [CWE-94](https://cwe.mitre.org/data/definitions/94.html)
- **Tags:** [Code injection](https://agentprime.io/advisories/tag/code-injection.md) · [CWE-15](https://agentprime.io/advisories/tag/cwe-15.md)
- **Published:** 19 Jun 2026
- **Updated:** 10 Sept 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 19 Jun 2026, 15:12 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `ouroboros-ai` (PyPI): affected `<0.42.1`; fixed in `0.42.1`

## Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

> Ouroboros-ai versions before 0.42.1 are vulnerable. An incomplete fix for CVE-2026-47211 left several execution-routing keys out of the untrusted \`.env\` denylist, and the working-directory MCP roster was also auto-loaded. A user who runs Ouroboros inside a malicious cloned repository can therefore have arbitrary commands executed, and can also weaken the approval gate. Upgrade to 0.42.1, which adds the missing keys and removes cwd auto-discovery. Until then, do not run Ouroboros from untrusted repository directories, and remove any project \`.env\` and \`./.ouroboros/mcp_servers.yaml\` first.

Written 1 Nov 2026.

## 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

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

- **CISA KEV:** Not listed.
- **EPSS:** 0.0024, the 15th percentile, on 5 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

- 31 Oct 2026, 14:11 UTC: First seen by agentprime
- 31 Oct 2026, 14:11 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-jv2h-4p9v-wf5w)

## Sources

- [GitHub Advisory Database: GHSA-jv2h-4p9v-wf5w](https://github.com/advisories/GHSA-jv2h-4p9v-wf5w)
- [OSV: GHSA-jv2h-4p9v-wf5w](https://osv.dev/vulnerability/GHSA-jv2h-4p9v-wf5w)
- <https://github.com/Q00/ouroboros/security/advisories/GHSA-jv2h-4p9v-wf5w>
- <https://github.com/Q00/ouroboros>

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-jv2h-4p9v-wf5w>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-jv2h-4p9v-wf5w/>. Everything for agents: <https://agentprime.io/llms.txt>.