Read the docs
TI-2026-41116 Aliases CVE-2026-57137GHSA-h2w2-v7j6-xqm4

PraisonAI AgentLoop onToolCall approval runs after tool execution

Priority HIGH 73CWE-693Published · Updated

Key facts

Attack vector
Network
Privileges required
Low
User interaction
None
Attack complexity
Low
Impact type
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-693.

Summary

PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, createAgentLoop() in src/praisonai-ts/src/ai/agent-loop.ts passes executable tools to generateText() before invoking the onToolCall approval callback. Because the wrapped AI SDK executes tool handlers during generation, a callback that returns false records tool_rejected only after the denied tool has already produced side effects and populated toolResults. Applications using onToolCall as a human or policy approval boundary can therefore execute rejected file, command, API, or data-modifying operations. This issue is fixed in version 1.7.2.

Why it matters now

Exploitation Proof of concept CISA SSVC · not in CISA KEV
EPSS 0.00506 43rd percentileScored 2026-11-07
Fix Fixed PraisonAI (MervinPraison): 1.7.2praisonai (npm): 1.7.2

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
MervinPraisonPraisonAI1.4.0 to before 1.7.21.7.2Patch availableCNA
—praisonai (npm)1.4.0 to before 1.7.21.7.2Patch availableGHSA-h2w2-v7j6-xqm4
  • PraisonAI VendorMervinPraison Affected 1.4.0 to before 1.7.2 Fixed in 1.7.2 Patch available CNA
  • praisonai (npm) Vendor— Affected 1.4.0 to before 1.7.2 Fixed in 1.7.2 Patch available GHSA-h2w2-v7j6-xqm4

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 1.7.2
  • Fix · GHSA-h2w2-v7j6-xqm4 praisonai (npm) Fixed in 1.7.2 Advisory →

Timeline

  1. 2026-10-02 Threatist record created from CVE-2026-57137
  2. 2026-10-03 Alias added: GHSA-h2w2-v7j6-xqm4

References

Other 4

  • 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