Verified

ghsa:GHSA-5C3V-H6HW-4GX7: praisonai <= 4.6.77

Duplicate Advisory: PraisonAI: Prompt-injection defense blocks only when 3+ detector families fire simultaneously; realistic single-vector injections pass through unblocked. Affected range: <= 4.6.77.

Affected technology

praisonai · <= 4.6.77
Vendor not specified by the source

Component: Not specified by the source

Attack conditions (Source advisory, CVSS 3.1): Network (remote) · No privileges required · No user interaction required

What an attacker can do

Attackers can craft single or double-vector prompt injections that are classified as HIGH threat level and pass through unblocked to reach the model. Source advisory’s CVSS 3.1 assessment rates confidentiality and availability impact as none; integrity impact as low.

Published 13-Oct-2026 07:48 UTC

Product: praisonai
KEV: no

Provenance

GitHub Advisory Database · Source record · observed 2026-10-09 03:17:07.463462+00:00 UTC

Stable permalink: https://cybercodered.org/item/adv-ghsa-ghsa-5c3v-h6hw-4gx7.html