Read the docs
TI-2026-79622 Aliases CVE-2026-57142

PraisonAI recipe policy bypass lets recipes run shell commands

Priority HIGH 69CWE-78Published · Updated

Key facts

Attack vector
Local
Privileges required
None
User interaction
Required
Attack complexity
Low
Impact type
Code execution, Security bypass
Confidentiality · integrity · availability
High · High · High
Fix status
Fixed

Attack profile from CVSS 3.1 · CNA. Fix status from CNA and GitHub. Impact type from CWE-78 and CWE-863.

Summary

PraisonAI from 4.5.87 before 4.6.61 checks dangerous tools only when they are declared in TEMPLATE.yaml requires.tools (CWE-863). A recipe can declare and approve the shell tool in workflow.yaml instead, so the allow_dangerous_tools=True flag is not required. An untrusted recipe that a user runs can then execute shell commands.

Written with Claude Haiku 5.5 from the sources below · 2026-10-29

Description from the CNA

PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.61, PraisonAI recipe execution has a dangerous-tool policy that is supposed to block default-denied tools unless the caller explicitly passes allow_dangerous_tools=True. That policy only checks tools declared in TEMPLATE.yaml requires.tools. For steps-based recipes, the actual execution path loads workflow.yaml with YAMLWorkflowParser. That parser resolves agent-level tools: declarations and preserves top-level approve:. Workflow.start() then installs those YAML-approved tools into the approval context. As a result, an untrusted recipe can omit execute_command from TEMPLATE.yaml requires.tools, declare it in workflow.yaml agents.*.tools, and add top-level approve: [execute_command]. The caller did not set allow_dangerous_tools=True, but the recipe policy allows the recipe and the workflow approval path self-approves the critical shell tool. This issue has been patched in version 4.6.61.

Why it matters now

Exploitation Proof of concept CISA SSVC · not in CISA KEV
EPSS 0.0024 15th percentileScored 2026-11-07
Fix Fixed PraisonAI (MervinPraison): 4.6.61praisonai (PyPI): 4.6.61

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
Poc
Automatable
No
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
MervinPraisonPraisonAI4.5.87 to before 4.6.614.6.61Patch availableCNA
—praisonai (PyPI)4.5.87 to before 4.6.614.6.61Patch availableGHSA-7qw2-w5rc-37x2
  • PraisonAI VendorMervinPraison Affected 4.5.87 to before 4.6.61 Fixed in 4.6.61 Patch available CNA
  • praisonai (PyPI) Vendor— Affected 4.5.87 to before 4.6.61 Fixed in 4.6.61 Patch available GHSA-7qw2-w5rc-37x2

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

Upgrade the praisonai PyPI package to version 4.6.61, which fixes this issue.

Written with Claude Haiku 5.5 from the sources below · 2026-10-29

  • Fix · CNA PraisonAI (MervinPraison) Fixed in 4.6.61
  • Fix · GHSA-7qw2-w5rc-37x2 praisonai (PyPI) Fixed in 4.6.61 Advisory →

Timeline

  1. 2026-10-23 Threatist record created from CVE-2026-57142
  2. 2026-10-24 Priority changed: MEDIUM → LOW
  3. 2026-10-29 CISA SSVC decision points changed
  4. 2026-10-29 Priority changed: LOW → HIGH

References

Other 2

  • 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

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences