CVE-2026-57137
PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, …
PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, createAgentLoop() in src/praisonai-ts/src/ai/agent-loop.ts passes executable tools to generateText() before invoking the onToolCall approval callback. Because the wrapped AI SDK executes tool handlers during generation, a callback that returns false records tool_rejected only after the denied tool has already produced side effects and populated toolResults. Applications using onToolCall as a human or policy approval boundary can therefore execute rejected file, command, API, or data-modifying operations. This issue is fixed in version 1.7.2.
What to do now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Set the orderSystems that can be reached from the internet come first, then the rest.
References
- github.com/MervinPraison/PraisonAI/security/advisories/GHSA-h2w2-v7j6-xqm4
- github.com/advisories/GHSA-h2w2-v7j6-xqm4
- github.com/MervinPraison/PraisonAI/commit/6b4b59fbe71a74983626c7a0cf7e10c47cd004f9
- github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62
- nvd.nist.gov/vuln/detail/CVE-2026-57137
- cve.org/CVERecord?id=CVE-2026-57137
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.