Answer in brief
CVE-2026-57120 records a Medium severity (CVSS 6.5) vulnerability in PraisonAI: execute_code sandbox bypass: str.format C-level attribute access reads every blocklisted dunder. The current sources do not mark it as known exploited. The current feed maps MervinPraison/praisonaiagents (generic). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 6.5. 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/praisonaiagents (generic). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| MervinPraison/praisonaiagentsgeneric | <1.6.59 | 1.6.59 |
Published upstream
Sep 14, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Sep 16, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Sep 14, 2026
PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, execute_code sandbox mode permits runtime assembly of blocklisted dunder names and allows str.format or str.format_map to resolve dotted fields through C-level attribute access that bypasses _safe_getattr. This exposes class, qualified-name, base-class, globals, and object-dictionary attributes to prompt-influenced code when approval is automatically granted, producing a high-impact read primitive without establishing a complete in-process execution chain. This issue is fixed in praisonaiagents 1.6.59.
Quoted source text, attributed separately from HOL analysis.