Read the docs

PraisonAI before 1.6.78 Remote Code Execution via CodeAgent

Priority HIGH 82CWE-94Published · Updated

Key facts

Attack vector
Network
Privileges required
None
User interaction
None
Attack complexity
Low
Attack requirements
None
Impact type
Code execution, Information disclosure
Confidentiality · integrity · availability
High · High · High
Fix status
Fixed

Attack profile from CVSS 4.0 · CNA. Fix status from CNA and GitHub. Impact type from CWE-94 and CWE-200.

Summary

PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python() that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LLM output through prompt injection to exfiltrate all environment secrets and execute arbitrary code on the host system.

Why it matters now

Exploitation Proof of concept CISA SSVC · not in CISA KEV
EPSS 0.1524 96th percentileScored 2026-11-07
Fix Fixed PraisonAI (MervinPraison): 1.6.78praisonaiagents (PyPI): 1.6.78

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
Poc
Automatable
Yes
Technical impact
Total

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 1.6.781.6.78Patch availableCNA
—praisonaiagents (PyPI)before 1.6.781.6.78Patch availableGHSA-2xv2-w8cq-5gxw
  • PraisonAI VendorMervinPraison Affected before 1.6.78 Fixed in 1.6.78 Patch available CNA
  • praisonaiagents (PyPI) Vendor— Affected before 1.6.78 Fixed in 1.6.78 Patch available GHSA-2xv2-w8cq-5gxw

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 1.6.78
  • Fix · GHSA-2xv2-w8cq-5gxw praisonaiagents (PyPI) Fixed in 1.6.78 Advisory →

Fixed in the same release

Records fixed by the same vendor advisory or release, as the CNA lists them.

  • Release ·

    MervinPraison PraisonAI 1.6.78

    2 records Highest priority Priority HIGH 2 HIGH

    Other records, highest priority first

    • TI-2026-44034 PraisonAI before 1.6.78 SSRF via Crawl4AI Chromium backendPriority HIGH 70

Timeline

  1. 2026-10-02 Threatist record created from CVE-2026-61447
  2. 2026-10-03 Alias added: GHSA-mhgx-w3w5-2rvc
  3. 2026-10-08 Alias added: GHSA-2xv2-w8cq-5gxw
  4. 2026-10-08 Fix available: PyPI/[email protected] · GHSA-2xv2-w8cq-5gxw
  5. 2026-10-08 CVSS score added · GHSA-2xv2-w8cq-5gxw
  6. 2026-10-08 Weakness changed · GHSA-2xv2-w8cq-5gxw
  7. 2026-10-08 3 new references · GHSA-2xv2-w8cq-5gxw
  8. 2026-10-26 EPSS moved to the 95th–99th percentile

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-2026-41123 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
  • TI-2026-41110 praisonai: Jobs API exposes agent-execution endpoints with no authentication CVSS 3.1CRITICAL 9.8
See all 177 →

Sources