PraisonAI before 4.6.78 Prompt Injection Defense Bypass
Key facts
- Attack vector
- Network
- Privileges required
- None
- User interaction
- None
- Attack complexity
- Low
- Attack requirements
- None
- Impact type
- Security bypass
- Confidentiality · integrity · availability
- High · None · None
- Fix status
- Fixed
Attack profile from CVSS 4.0 · CNA. Fix status from CNA and GitHub. Impact type from CWE-693.
Summary
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.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- Poc
- Automatable
- Yes
- Technical impact
- Partial
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
| Vendor | Product | Affected versions | Fixed in | Status | Source |
|---|---|---|---|---|---|
| MervinPraison | PraisonAI | before 4.6.78 | 4.6.78 | Patch available | CNA |
| — | PraisonAI (PyPI) | before 4.6.78 | 4.6.78 | Patch available | GHSA-fj8f-m44g-c479 |
- PraisonAI VendorMervinPraison Affected before 4.6.78 Fixed in 4.6.78 Patch available CNA
- PraisonAI (PyPI) Vendor— Affected before 4.6.78 Fixed in 4.6.78 Patch available GHSA-fj8f-m44g-c479
CPE names Threatist (inferred) · 1
Inferred from how NVD named this product before; not given by a source.
| CPE | Versions | Role | Vendor |
|---|---|---|---|
| cpe:2.3:a:praison:praisonai:*:*:*:*:*:*:*:* | — | — | MervinPraison |
- cpe:2.3:a:praison:praisonai:*:*:*:*:*:*:*:* Versions — — ·MervinPraison
Remediation
- Fix · CNA PraisonAI (MervinPraison) Fixed in 4.6.78
- Fix · GHSA-fj8f-m44g-c479 PraisonAI (PyPI) Fixed in 4.6.78 Advisory →
Fixed in the same release
Records fixed by the same vendor advisory or release, as the CNA lists them.
- Release ·
MervinPraison PraisonAI 4.6.78
5 records Highest priority Priority HIGH 4 HIGH, 1 MEDIUM
Other records, highest priority first
- TI-2026-42820 PraisonAI before 4.6.78 SQL/CQL Injection via vector dimensionPriority HIGH 81
- TI-2026-44050 PraisonAI before 4.6.78 Arbitrary File Write and Command ExecutionPriority HIGH 76
- TI-2026-44033 PraisonAI AgentMail before 4.6.78 Message Injection via WebhookPriority HIGH 70
Timeline
- 2026-10-02 Threatist record created from CVE-2026-61439
- 2026-10-03 Alias added: GHSA-5r2q-3wg3-57m2
- 2026-10-07 Alias added: GHSA-fj8f-m44g-c479
- 2026-10-07 Fix available: PyPI/[email protected] · GHSA-fj8f-m44g-c479
- 2026-10-07 CVSS score added · GHSA-fj8f-m44g-c479
- 2026-10-07 Weakness changed · GHSA-fj8f-m44g-c479
- 2026-10-07 3 new references · GHSA-fj8f-m44g-c479
References
More MervinPraison vulnerabilities
- TI-2026-79619 Missing authentication in PraisonAI AgentOS exposes agent chat CVSS 3.1CRITICAL 9.8
- TI-2026-71236 Missing access control in PraisonAI AgentTeam exposes agent endpoints CVSS 3.1CRITICAL 9.8
- TI-2026-44052 PraisonAI before 1.6.78 Remote Code Execution via CodeAgent CVSS 4.0CRITICAL 10.0
- TI-2026-41123 praisonai-platform 0.1.4 still boots on the hardcoded JWT secret dev-secret-change-me (default-open production guard) CVSS 3.1CRITICAL 9.8
- TI-2026-41122 praisonai-platform: default JWT signing secret 'dev-secret-change-me' enables token forgery CVSS 3.1CRITICAL 9.8
- TI-2026-41118 PraisonAI MCPServer exposes unauthenticated HTTP tools/call CVSS 3.1CRITICAL 9.8
Sources
- CVE-2026-61439 · CVE Program
- CVE-2026-61439 · NVD
- FIRST EPSS
- GHSA-5r2q-3wg3-57m2 · GitHub Advisory Database · CC BY 4.0
- GHSA-fj8f-m44g-c479 · GitHub Advisory Database · CC BY 4.0
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences