Answer in brief
CVE-2026-57138 records a Unknown severity vulnerability in PraisonAI codeMode sandbox escape via Function constructor. The current sources do not mark it as known exploited. The current feed maps MervinPraison/PraisonAI (generic). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
A CVSS score is not reported in the current record. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps MervinPraison/PraisonAI (generic). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| MervinPraison/PraisonAIgeneric | >= 1.4.0, < 1.7.2 | Not reported |
Published upstream
Sep 15, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Sep 15, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Sep 15, 2026
PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, codeMode in src/praisonai-ts/src/tools/builtins/code-mode.ts executes untrusted JavaScript with new Function() inside with(sandbox) and relies on a small source-code blocklist plus shadowed process and require properties. Code can use ({}).constructor.constructor to recover the real Function constructor, obtain process and process.mainModule.require, and reach host filesystem and subprocess APIs despite the advertised sandbox. Attackers who control codeMode input can read secrets, modify files, execute commands, or exhaust the host process. This issue is fixed in version 1.7.2.
Quoted source text, attributed separately from HOL analysis.