Tools AI Risk Radar ai-incident-0141
Incident record
PraisonAI fixes a prompt-injection blocking gap
- Severity
- High
- Status
- Patched
- Type
- Prompt Injection
- Target
- PraisonAI
- Actor
- researcher
- CVE
- CVE-2026-61439
What happened
Its default defence could flag malicious instructions as high risk yet still pass them to the model. The blocking threshold required several detection checks to fire together.
PraisonAI: affected <= 4.6.77; fixed in 4.6.78. The date shown is the maintainer’s original disclosure date. Its advisory assigns 7.5 under CVSS 3.1.
Sources
- Primary disclosuregithub.com/MervinPraison/PraisonAI/security/advisories/GHSA-…
One record from the AI Risk Radar, maintained by the Security Desk.Data: CSV · JSON ·RSS · CC BY 4.0 with attribution to YFarmX.Tracker updated · 13 October 2026