https://cve.radiocsirt.org/rss/recent/all/10 Most recent entries from all 2026-10-09T23:08:01.526758+00:00 Vulnerability-Lookup csirt@opendfir.org python-feedgen Contains only the most 10 recent entries. https://cve.radiocsirt.org/vuln/euvd-2026-336464 EUVD-2026-336464 2026-10-09T23:08:01.529580+00:00 EUVD-2026-336464 https://cve.radiocsirt.org/vuln/fkie_cve-2026-61439 fkie_cve-2026-61439 2026-10-09T23:08:01.529612+00:00

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.

 https://cve.radiocsirt.org/vuln/ghsa-5r2q-3wg3-57m2 Withdrawn: GHSA-5r2q-3wg3-57m2 — Duplicate Advisory: PraisonAI: Prompt Injection Defense Bypassed for HIGH-Level Threats 2026-10-09T23:08:01.529649+00:00

Withdrawn by the publisher.

Affected: PyPI: praisonai

### Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-fj8f-m44g-c479. This link is maintained to preserve external references.

### Original 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.