CVE-2026-57137
גבוהה 8.8
תיאור (מקור, אנגלית)
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.
מדדים
- CVSS 3.1
-
8.8 (HIGH)
מקור הציון: CNA
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H - EPSS — סבירות ניצול
- 1% (אחוזון 000) נכון ל-28/9/2026
- CWE
- CWE-693, CWE-862, CWE-863
קישורים
- https://github.com/MervinPraison/PraisonAI/commit/6b4b59fbe71a74983626c7a0cf7e…
- https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-h2w2-v7j6-…
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-h2w2-v7j6-…