Skip to main content
VulnerabilityPublished

CVE-2026-57137: MervinPraison PraisonAI · Protection Mechanism Failure

Affects MervinPraison PraisonAISource CVE Database V5

0
Compare

Not known to be exploited · CVSS 8.8 High : upgrade to 1.7.2 soon.

Data as of 30 Oct 2026, 11:52 UTC

CVSS 3.1 base score
8.8High
How severe the flaw is on the 0–10 CVSS scale.
EPSS
0.5% chance of exploitation in 30 days – higher than 43% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch
Available – fixed in 1.7.2
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 15 Sep 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponized: no evidence on record.

    No public exploit code indexed in Metasploit or Exploit-DB

  4. Exploited in the wild: no evidence on record.

    Not in CISA KEV and no source reports exploitation

  5. Observed by OffSeq Mirage: no evidence on record.

    No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 30 Oct 2026.

What to do

Upgrade PraisonAI and mervinpraison/PraisonAI to 1.7.2.

Affected software

ProductAffectedFixed in
MervinPraisonPraisonAIAffected
  • >=1.4.0 <1.7.2
Fixed in
  • 1.7.2
GitHubmervinpraison/PraisonAIpkg:github/mervinpraison/PraisonAIOther threatsAffected
  • >=1.4.0 <1.7.2
Fixed in
  • 1.7.2

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

Upgrade PraisonAI to version 1.7.2 or later, where this issue is fixed. No other mitigation is indicated by the vendor advisory.

Description

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.

References

Community reviews

Loading reviews…