Vulnerability · Published Sep 14, 2026 · Assigned by GitHub_M

CVE-2026-57120PraisonAI: execute_code sandbox bypass: str.format C-level attribute access reads every blocklisted dunder

Medium 6.5

In plain English

A medium-severity security flaw in praisonaiagents from MervinPraison. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.6% (higher than 46% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)6.5Medium

Exploit odds (30 days)0.6%top 53.5% of all CVEs

Exploited in the wildNo reportsCISA SSVC: poc

Attack toolingNoneno public tooling known

Official description

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.

Affected packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
PyPI	praisonaiagents	1.6.59	GHSA-pv2j-rghr-v5r9
PyPI	praisonaiagents	1.6.59	PYSEC-2026-3533

Affected products (as reported)

Vendor	Product	Versions
MervinPraison	praisonaiagents	< 1.6.59

Weakness: CWE-693 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N

References

https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-pv2j-rghr-v5r9 x_refsource_CONFIRM
https://github.com/MervinPraison/PraisonAI/commit/2adfe7e8323f6deec66925cf15a885b6238895e9 x_refsource_MISC
https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.59 x_refsource_MISC