CVE-2026-61439
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.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.43%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
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.
- CVSS 4.0
- 8.7 HIGHCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/M
- EPSS
- 0.43% probability · 37th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-1188
- Source
- disclosure@vulncheck.com
References
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.