CVE Catalog

CVE-2026-57120

MediumCVSS 6.5
Published: Translated: NVD NIST

Summary

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.

Risk Assessment

Attackers can exploit this weakness to read sensitive server data such as environment variables, keys, or internal objects, potentially leading to privilege escalation or data exfiltration.

Recommendation

Upgrade praisonaiagents to version 1.6.59 or later, which mitigates this primitive. Additionally, consider manual approval of code execution instead of automatic.

Other vulnerabilities in PraisonAI agents

See all
Original NVD description (English source)

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.

Vulnerability data from NVD (NIST) · CISA KEV · EPSS