HIGH

CVE-2026-57130

2026-09-14 CVSS v3.1

CVSS

8.1

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.

Weakness (CWE)

CWE-20 Improper Input Validation

CWE-77 Command Injection

EPSS Score

0.35%

Probability of exploitation in next 30 days

28.2th percentile

References

https://github.com/MervinPraison/PraisonAI/commit/b4270173d4123fb1ee8910588f0896668ee21b59 https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.59 https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-c969-5x3p-vq3v

View on dbcve.org

Base CVE data derived from NVD (public domain). Enrichment by dbcve.org (CC-BY-4.0). Fetched via API.

Back to CVE