Skip to main content

CVE-2026-56832: CWE-345: Insufficient Verification of Data Authenticity in MervinPraison PraisonAI

0
High
VulnerabilityCVE-2026-56832cvecve-2026-56832cwe-345cwe-863
Published: 10/23/2026 (10/23/2026, 11:55:53 UTC)
Source: CVE Database V5
Vendor/Project: MervinPraison
Product: PraisonAI

Description

PraisonAI versions from 4.5.2 up to but not including 4.6.59 contain a vulnerability in the Discord approval backend where any user able to post in the configured approval channel can approve a pending high-risk tool call by sending a message classified as approval (e.g., 'yes'). This occurs because the system does not verify that the approval message is a direct reply or otherwise bound to the approval request, allowing unthreaded channel cross-talk. The Slack and Telegram approval backends also lack explicit approver allowlist parameters, but the primary issue is with Discord. This vulnerability has been patched in version 4.6.59.

CVSS v3.1

Score 8.8high

Attack Vector
Network
Attack Complexity
Low
Privileges Required
Low
User Interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

Affected software

MervinPraison

PraisonAI

Affected versions
>=4.5.2 <4.6.59
GitHub Actionsmore threats →ai
mervinpraison/PraisonAI
pkg:github/mervinpraison/PraisonAI
Affected versions
>=4.5.2 <4.6.59

Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 10/23/2026, 12:30:45 UTC

Technical Analysis

CVE-2026-56832 describes an insufficient verification of data authenticity vulnerability (CWE-345) in MervinPraison's PraisonAI multi-agent teams system. Specifically, in versions >=4.5.2 and <4.6.59, the DiscordApproval component approves pending dangerous tool calls upon detecting any later non-bot message in the configured Discord channel whose text is classified as approval (e.g., 'yes'). The approval message does not need to be a reply or linked to the original request, enabling any user who can post in the approval channel to authorize high-risk actions. The Slack and Telegram backends also lack explicit approver allowlists but the main exploitable vector is the unthreaded Discord channel cross-talk. The issue is fixed in version 4.6.59.

Potential Impact

An attacker with permission to post messages in the configured Discord approval channel can approve pending high-risk tool calls without explicit authorization, potentially leading to unauthorized execution of dangerous actions. This can result in full confidentiality, integrity, and availability compromise of the system as indicated by the CVSS impact metrics (C:H/I:H/A:H).

Mitigation Recommendations

Upgrade PraisonAI to version 4.6.59 or later, where this vulnerability is patched. The fix addresses the insufficient verification by ensuring approval messages are properly bound to the approval request, preventing unthreaded cross-talk approvals. No other mitigations are specified or necessary once patched.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Data Version
5.2
Assigner Short Name
GitHub_M
Date Reserved
2026-06-23T14:55:09.117Z
Cvss Version
3.1
State
PUBLISHED

Threat ID: 6adb50114d27ba8daa216e89

Added to database: 10/23/2026, 12:16:17 UTC

Last enriched: 10/23/2026, 12:30:45 UTC

Last updated: 10/23/2026, 13:31:46 UTC

Views: 2

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

Need more coverage?

Upgrade to Pro Console for AI refresh and higher limits.

For incident response and remediation, OffSeq services can help resolve threats faster.

Latest Threats

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses