VYPR
High severity8.1NVD Advisory· Published Sep 14, 2026· Updated Sep 15, 2026

CVE-2026-57130

CVE-2026-57130

Description

PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, src/praisonai-agents/praisonaiagents/tools/email_tools.py interpolates LLM-controlled from_addr, subject, and query values directly into quoted IMAP SEARCH criteria. Embedded quote, backslash, newline, or null characters can escape the intended criterion and alter IMAP operations when search_emails, reply_email, or archive_email is exposed to an agent with configured email credentials, allowing mailbox data access, modification, deletion, or connection disruption. This issue is fixed in praisonaiagents 1.6.59.

AI Insight

LLM-synthesized narrative grounded in this CVE's description and references.

Affected packages

Versions sourced from the GitHub Security Advisory.

PackageAffected versionsPatched versions
praisonaiagentsPyPI
< 1.6.591.6.59

Affected products

3

Patches

Vulnerability mechanics

References

4

News mentions

0

No linked articles in our index yet.