PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, createAgentLoop() in…
Historical advisory recorded 25 Oct 2026 14:19:10 UTC. Read the latest advisory.
nvd · CVE-2026-57137
PublishedPraisonAI 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.
Read the publisher's advisoryAffected versions, risk and source history
nvd · CVE-2026-57137
PublishedNVD analysis and CPE criteria are source context, not proof that a package or your environment is affected. Complete affected data, logical configurations and SSVC are retained in the original JSON.
Source analysis status: Deferred
Weakness classifications: CWE-693 · CWE-862 · CWE-863
Original publisher date fields
published: 2026-09-15T11:17:11.030
lastModified: 2026-09-15T14:45:28.563
No normalized affected-package data is projected for this source revision. The original publisher record may contain additional product and version evidence; this does not establish that a package is unaffected.
Original source record · Cite this exact observation · Complete original publisher JSON