Home

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.

PUBLISHED Reserved 2026-07-08 | Published 2026-07-10 | Updated 2026-07-14 | Assigner VulnCheck




MEDIUM: 6.9CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N
MEDIUM: 5.3CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N

Problem types

Protection Mechanism Failure

Product status

Default status
unaffected

Any version before 4.6.78
affected

4.6.78 (semver)
unaffected

Credits

SnailSploit reporter

References

github.com/...isonAI/security/advisories/GHSA-4r3p-w3mc-5v34 exploit

github.com/...isonAI/security/advisories/GHSA-4r3p-w3mc-5v34 (GitHub Security Advisory (GHSA-4r3p-w3mc-5v34)) vendor-advisory

www.vulncheck.com/...-before-prompt-injection-defense-bypass (VulnCheck Advisory: PraisonAI before 4.6.78 Prompt Injection Defense Bypass) third-party-advisory

cve.org (CVE-2026-60086)

nvd.nist.gov (CVE-2026-60086)

Download JSON