What is the CVSS score of CVE-2026-55534?

CVE-2026-55534 has a CVSS 3.1 base score of 8.6 (High). CVSS vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:H. EPSS exploitation probability: 0.3%.

Which versions of PraisonAI are affected by CVE-2026-55534?

PraisonAI versions 4.6.34 through 4.6.57 contain a critical authentication bypass in the agent execution endpoints, allowing unauthenticated remote attackers to invoke configured agents and…. A patch is available.

Is there a public PoC exploit available for CVE-2026-55534?

Yes, a public proof-of-concept exploit is available for CVE-2026-55534. Prioritise patching immediately. EPSS: 0.3%.

How to fix or mitigate CVE-2026-55534?

Within 24 hours, identify all systems running PraisonAI versions 4.6.34 through 4.6.57 and assess their network exposure; immediately restrict network access to agent endpoints if applicable. Within 7 days, upgrade all affected instances to PraisonAI v4.6.58 or later, which includes the _authorise_request() method enforcing Bearer token and X-Auth-Token header validation. Within 30 days, audit agent execution logs for the affected timeframe to identify any unauthorized invocations and verify no exploitation occurred.

PraisonAI CVE-2026-55534

EUVD-2026-65500 HIGH

Missing Authentication for Critical Function (CWE-306)

2026-08-25 GitHub_M

GHSA-7ww9-85pg-cv4x

Authentication Bypass Praisonai

8.6

CVSS 3.1 · Vendor: GitHub_M

Severity by source

Vendor (GitHub_M) PRIMARY

8.6 HIGH

AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:H

vuln.today AI

8.6 HIGH

Network-reachable with no credentials or interaction needed; C:L/I:L reflects baseline agent invocation with A:H for unauthenticated resource consumption; S:U as scope is bounded by agent configuration.

3.1 AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:H

4.0 AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:H/SC:N/SI:N/SA:N

Primary rating from Vendor (GitHub_M).

CVSS VectorVendor: GitHub_M

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:H

Attack Vector

Network

Attack Complexity

Low

Privileges Required

None

User Interaction

None

Scope

Unchanged

Confidentiality

Low

Integrity

Low

Availability

High

Lifecycle Timeline

Patch available

Aug 25, 2026 - 16:02 EUVD

Source Code Evidence Fetched

Aug 25, 2026 - 15:17 vuln.today

Analysis Generated

Aug 25, 2026 - 15:17 vuln.today

CVE Published

Aug 25, 2026 - 14:41 cve.org

HIGH 8.6

DescriptionCVE.org

PraisonAI is a multi-agent teams system. From praisonai 4.6.34 until 4.6.58, praisonai serve agents accepts --api-key but _create_agents_app() does not authenticate POST /agents or POST /agents/{agent_name}. A network caller can invoke configured agents without credentials even when an API key was supplied. This issue is fixed in version 4.6.58.

AnalysisAI

Unauthenticated remote agent invocation in PraisonAI versions 4.6.34 through 4.6.57 allows any network-reachable caller to execute configured agents via POST /agents and POST /agents/{agent_name} despite an operator-supplied --api-key. The FastAPI app created by _create_agents_app() accepts the key at the CLI layer but never applies it as middleware or a route dependency, rendering the documented authentication control entirely inert on those endpoints. …

Unlock full vulnerability intelligence

Risk assessment & exploitation conditions
Attack chain visualization
Remediation with exact patch versions
Threat intelligence from 22 sources
Personal watchlist & email alerts

Continue with Google Continue with GitHub

Free forever · No credit card required

Attack ChainAIDerived

Hypothetical attack flow derived from CVE metadata

Access

Identify internet-exposed PraisonAI serve agents port

Delivery

Send unauthenticated POST to /agents or /agents/{agent_name}

Exploit

Bypass absent auth middleware in _create_agents_app()

Execution

Trigger direct agent execution

Impact

Leverage agent tool permissions for data access or further action