Vulnerability · Published Jul 10, 2026 · Assigned by VulnCheck

CVE-2026-60086PraisonAI before 4.6.78 Prompt Injection Defense Bypass

Medium 5.3

In plain English

A medium-severity security flaw in PraisonAI from MervinPraison. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.3% (higher than 19% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)5.3Medium

Exploit odds (30 days)0.3%top 81.2% of all CVEs

Exploited in the wildNo reportsCISA SSVC: poc

Attack toolingNoneno public tooling known

Official 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.

Affected packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
PyPI	praisonai	4.6.78	GHSA-4r3p-w3mc-5v34
PyPI	praisonai	4.6.78	PYSEC-2026-4248

Affected products (as reported)

Vendor	Product	Versions
MervinPraison	PraisonAI	0 – before 4.6.78

Weakness: CWE-693 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N

References

GitHub Security Advisory (GHSA-4r3p-w3mc-5v34) vendor-advisory
VulnCheck Advisory: PraisonAI before 4.6.78 Prompt Injection Defense Bypass third-party-advisory