CVE-2026-57133 PraisonAI utility shell safe-command wrapper allowlist bypass via shell chaining
Attackers can execute arbitrary commands by chaining shell syntax to allowlisted commands in PraisonAI's utility tools.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-57133?
CVE-2026-57133 is a high-severity command injection vulnerability in MervinPraison PraisonAI, published on 15 Sep 2026. Any signed-in user can exploit it over the network, with no action from the victim.
Official description
PraisonAI is a multi-agent teams system. From 1.5.1 until 1.7.2, the shell() helper exported from src/praisonai-ts/src/tools/utility-tools.ts checks only the first whitespace-delimited token against safeCommands and then passes the complete original string to child_process.exec(). A string that starts with an allowed read-only command can append a second non-allowlisted command through shell syntax, allowing arbitrary command execution with the PraisonAI process privileges. This issue is fixed in version 1.7.2.
Which versions are affected by CVE-2026-57133?
2 open source packages ship an affected version, including praisonai.
| Package | Affected | Fixed in |
|---|---|---|
praisonai npm | From 1.5.1 | 1.7.2 |
praisonai npm | From 1.5.1 | 1.7.2 |
How do I fix CVE-2026-57133?
Upgrade praisonai to 1.7.2 or later.
Upgrade, and pass arguments to programs as a list instead of through a shell. More about Command injection.
Is CVE-2026-57133 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-57133 exists.
Sources
Also known as GHSA-5jv7-2mjm-h6qj.