CVE-2026-60086
MEDIUM
5.3
CVSS 3.1
Description
PraisonAI before 4.6.78 contains a prompt injection defense bypass vulnerability where the injection defense only blocks threats classified as CRITICAL, requiring three or more detector families to match simultaneously. Attackers can craft single or double-vector prompt injections that are classified as HIGH threat level and pass through unblocked to reach the model.
Metadata
Severity & Metrics
5.3
MEDIUM CVSS 3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N
Affected products (1)
| Vendor | Product | Platform | Versions |
|---|---|---|---|
| MervinPraison | PraisonAI | — | 0 < 4.6.78, 4.6.78 |
Weakness (CWE)
| CWE | Source | Description |
|---|---|---|
| CWE-693 | cna | Protection Mechanism Failure |
CVSS scores (2)
| Score | Severity | Version | Source | Vector |
|---|---|---|---|---|
| 6.9 | MEDIUM | 4.0 | cna | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N |
| 5.3 | MEDIUM | 3.1 | cna | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N |
References (2)
- GitHub Security Advisory (GHSA-4r3p-w3mc-5v34) https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4r3p-w3mc-5v34
- VulnCheck Advisory: PraisonAI before 4.6.78 Prompt Injection Defense Bypass https://www.vulncheck.com/advisories/praisonai-before-prompt-injection-defense-bypass