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.
{
"cna_assigner": "GitHub_M",
"cwe_ids": [
"CWE-693",
"CWE-862",
"CWE-863"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/57xxx/CVE-2026-57137.json"
}{
"extracted_events": [
{
"introduced": "1.4.0"
},
{
"fixed": "1.7.2"
}
],
"source": [
"AFFECTED_FIELD",
"REFERENCES"
]
}