Read the docs

PraisonAI before 4.6.78 Prompt Injection Defense Bypass

Priority HIGH 70CWE-693Published · Updated

Key facts

Attack vector
Network
Privileges required
None
User interaction
None
Attack complexity
Low
Attack requirements
None
Impact type
Security bypass
Confidentiality · integrity · availability
None · Low · None
Fix status
Fixed

Attack profile from CVSS 4.0 · CNA. Fix status from CNA and GitHub. Impact type from CWE-693.

Summary

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.

Why it matters now

Exploitation Proof of concept CISA SSVC · not in CISA KEV
EPSS 0.00266 18th percentileScored 2026-11-07
Fix Fixed PraisonAI (MervinPraison): 4.6.78praisonai (PyPI): 4.6.78

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

VendorProductAffected versionsFixed inStatusSource
MervinPraisonPraisonAIbefore 4.6.784.6.78Patch availableCNA
—praisonai (PyPI)before 4.6.784.6.78Patch availableGHSA-4r3p-w3mc-5v34
  • 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-4r3p-w3mc-5v34

CPE names Threatist (inferred) · 1

Inferred from how NVD named this product before; not given by a source.

CPEVersionsRoleVendor
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-4r3p-w3mc-5v34 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-2026-44049 PraisonAI before 4.6.78 Code Injection via f-stringPriority HIGH 76
    • TI-2026-44039 PraisonAI before 4.6.78 Allowlist Bypass via find -execPriority HIGH 73
    • TI-2026-42821 PraisonAI before 4.6.78 Unauthenticated SSRF via webhook_urlPriority HIGH 70

Timeline

  1. 2026-10-02 Threatist record created from CVE-2026-60086
  2. 2026-10-03 Alias added: GHSA-5c3v-h6hw-4gx7
  3. 2026-10-09 Alias added: GHSA-4r3p-w3mc-5v34
  4. 2026-10-09 Fix available: PyPI/[email protected] · GHSA-4r3p-w3mc-5v34
  5. 2026-10-09 CVSS score added · GHSA-4r3p-w3mc-5v34
  6. 2026-10-09 Weakness changed · GHSA-4r3p-w3mc-5v34
  7. 2026-10-09 3 new references · GHSA-4r3p-w3mc-5v34

References

  • 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
See all 177 →

Sources