# GPT-Pilot contains a command injection vulnerability in the Executor.run() method

Advisory record · `GHSA-m85w-whwh-qvfx`

- **Identifiers:** `GHSA-m85w-whwh-qvfx` · `CVE-2026-31246` · `PYSEC-2026-2501`
- **State:** Confirmed
- **Severity:** CVSS 6.5 Medium
- **Critical:** No
- **Weakness (CWE):** [CWE-78](https://cwe.mitre.org/data/definitions/78.html)
- **Tags:** [Command injection](https://agentprime.io/advisories/tag/command-injection.md)
- **Published:** 11 May 2026
- **Updated:** 13 Jul 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 11 May 2026, 18:31 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `gpt-pilot` (PyPI): affected `<=0.0.10`; no fixed version yet

## Machine-written summary

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

> GPT-Pilot versions up to and including 0.0.10 contain a command injection flaw in the Executor.run() method. When the tool asks the user to confirm or edit a command, it passes the free-text input directly to a shell without validation, so an attacker who can supply that input could run arbitrary shell commands with the privileges of the GPT-Pilot process. No fix is listed.

Written 6 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

- 6.5 Medium, CVSS 3.1: `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N`, from GitHub Advisory Database

- **CISA KEV:** Not listed.
- **EPSS:** 0.0070, the 53rd percentile, on 15 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

- 31 Oct 2026, 15:01 UTC: First seen by agentprime
- 31 Oct 2026, 15:01 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-m85w-whwh-qvfx)

## Sources

- [GitHub Advisory Database: GHSA-m85w-whwh-qvfx](https://github.com/advisories/GHSA-m85w-whwh-qvfx)
- [OSV: GHSA-m85w-whwh-qvfx](https://osv.dev/vulnerability/GHSA-m85w-whwh-qvfx)
- <https://nvd.nist.gov/vuln/detail/CVE-2026-31246>
- <https://github.com/Pythagora-io/gpt-pilot>
- <https://www.notion.so/CVE-2026-31246-35d1e1393188812ea3c6c88ad28d3d57>

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-m85w-whwh-qvfx>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-m85w-whwh-qvfx/>. Everything for agents: <https://agentprime.io/llms.txt>.