CVE-2026-57137
- Published15 Sept 2026
Description
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.
CVSS 3.1 breakdown
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:HRemediation
No fixed version is recorded in the NVD data. Check the vendor advisory for the latest guidance.
References
Related CVEs
Recent high-severity vulnerabilities sharing a weakness type.
Frequently asked
Is CVE-2026-57137 being actively exploited?
CVE-2026-57137 is not in the CISA KEV catalog. Its EPSS exploit probability is 0.44%.
How severe is CVE-2026-57137?
CVE-2026-57137 has a CVSS 3.1 base score of 8.8, rated high. EPSS estimates a 0.44% probability of exploitation.
How do I fix CVE-2026-57137?
Apply the vendor's patch or advisory guidance, then verify no affected versions remain across your devices.
How Secuno handles this
Secuno correlates vulnerabilities like CVE-2026-57137 against the real software inventory on every managed device, every day. Rather than a static severity, each match is scored in context: exploit availability, EPSS, the asset's exposure, and business criticality decide where it lands in the queue. If an affected version is present anywhere across your portfolio, it surfaces automatically with a prioritised remediation path.
Data from the NVD, CISA KEV catalog and FIRST EPSS. CVSS 3.1 base score shown where available.