Home

Description

PraisonAI versions before 4.6.78 contain a prompt injection defense misconfiguration where the block threshold defaults to CRITICAL severity, allowing HIGH-level threats to pass through unblocked. Attackers can submit single-vector prompt injection attacks such as instruction overrides or financial manipulation that trigger HIGH severity detection but are logged without blocking, enabling system prompt extraction and unauthorized tool invocations.

PUBLISHED Reserved 2026-07-09 | Published 2026-07-11 | Updated 2026-07-14 | Assigner VulnCheck




HIGH: 8.7CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N
HIGH: 7.5CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

Problem types

Initialization of a Resource with an Insecure Default

Product status

Default status
unaffected

Any version before 4.6.78
affected

4.6.78 (semver)
unaffected

Credits

chakrapani150 reporter

References

github.com/...isonAI/security/advisories/GHSA-fj8f-m44g-c479 exploit

github.com/...isonAI/security/advisories/GHSA-fj8f-m44g-c479 (GitHub Security Advisory (GHSA-fj8f-m44g-c479)) 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-2026-61439)

nvd.nist.gov (CVE-2026-61439)

Download JSON