Description
MindsDB Minds Platform version 26.1.0 and earlier contains an unauthenticated remote code execution vulnerability that allows unauthenticated attackers to execute arbitrary OS commands by submitting crafted prompts to the unprotected POST /api/v1/responses/ endpoint, which reaches the Anton agent's scratchpad tool that calls exec() on attacker-influenced Python source without sandboxing. Attackers can first configure their own LLM API key through the unauthenticated PUT /api/v1/settings/ endpoint, then POST a prompt directing the agent to invoke the scratchpad tool with arbitrary Python code, achieving full OS command execution as the user running the desktop application and enabling access to SSH keys, stored credentials, and environment secrets.
Affected products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| MindsDB | Minds Platform | ≤ 26.1.0 | — |
Public exploits
Exploit or proof-of-concept code for this vulnerability is publicly available, which lowers the bar for attackers. Treat it as a reason to patch sooner.
GitHub 1 repository
-
Boreas37/CVE-2026-73678-PoC ★ 1 · Aug 16, 2026
CVE-2026-73678 — MindsDB Minds Platform unauthenticated RCE via scratchpad exec (CVSS 10.0). Verified end-to-end with real LLM
Sources: PoC-in-GitHub, Metasploit Framework, Exploit-DB — updated daily. Only links are listed; no exploit code is hosted here.
References
- Product Repository product
- GitHub Security Advisory (GHSA-jcxw-h8ph-pxpv) vendor-advisory
- https://www.vulncheck.com/advisories/mindsdb-minds-platform-unauthenticated-rce-via-scratchpad-exec third-party-advisory