CVE-2026-57137
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.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.51%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
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
- 8.8 HIGHCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
- EPSS
- 0.51% probability · 43th percentile
- Public exploits
- None in Exploit-DB
- CISA KEV
- Not listed
- Weakness
- CWE-693, CWE-862, CWE-863
- Source
- security-advisories@github.com
EPSS 0.5% since 26 October 2026; no change recorded yet. Points are recorded when the score first appears and whenever it moves by a percentage point or more.
References
- https://github.com/MervinPraison/PraisonAI/commit/6b4b59fbe71a74983626c7a0cf7e10c47cd004f9
- https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-h2w2-v7j6-xqm4
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-h2w2-v7j6-xqm4
Source: NVD record, EPSS from FIRST.org, KEV from CISA, exploits from Exploit-DB. Refreshed daily. Download this record as JSON.