[ CVE-2026-61439 · Published 11 Jul 2026 ]
PraisonAI: Prompt Injection Defense Bypassed for HIGH-Level Threats
CVSS 7.5
EPSS <1%Fix available
[ Why it matters ]Priority signals
- Public proof-of-concept exploit exists (CISA SSVC)
[ Description ]Official description
PraisonAI versions before 4.6.78 contain a prompt injection defense misconfiguration where the block threshold defaults to CRITICAL severity, allowing HIGH-level threats to pass through unblocked. Attackers can submit single-vector prompt injection attacks such as instruction overrides or financial manipulation that trigger HIGH severity detection but are logged without blocking, enabling system prompt extraction and unauthorized tool invocations.
[ Fixes ]Fixes and patches
- PraisonAI 4.6.78Fixed version · GitHub Advisories · pip package PraisonAI: upgrade to 4.6.78 or later (affected <= 4.6.77)
[ Packages ]Affected open-source packages
- PraisonAI pipAffected <= 4.6.77 · fixed in 4.6.78 · GHSA-fj8f-m44g-c479