CVE-2026-44339VulnerabilityPublished 11 May 2026

Praisonaiagents: PraisonAI has unsafe tool resolution

Affects praisonaiagentsSource GCVE Database

Authoritative record:CVE-2026-44339· High 8.6

Not known to be exploited · CVSS 8.6 High : upgrade to 1.6.37 soon.

Data as of 27 Oct 2026, 00:58 UTC

CVSS 3.1 base score

8.6High

How severe the flaw is on the 0–10 CVSS scale.

Patch: Available – fixed in 1.6.37, 4.6.37

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

Attack Vector: Network
Attack Complexity: Low
Privileges Required: None
User Interaction: None
Scope: Unchanged
Confidentiality: Low
Integrity: High
Availability: Low

Bold values are the worst case: easiest to exploit or largest impact.

Attack Vector: Network: The vulnerable component is bound to the network stack and the set of possible attackers extends beyond the other options listed, up to and including the entire Internet. Such a vulnerability is often termed 'remotely exploitable' and can be thought of as an attack being exploitable at the protocol level one or more network hops away (e.g., across one or more routers).
Attack Complexity: Low: Specialized access conditions or extenuating circumstances do not exist. An attacker can expect repeatable success against the vulnerable component.
Privileges Required: None: The attacker is unauthorized prior to attack, and therefore does not require any access to settings or files to carry out an attack.
User Interaction: None: The vulnerable system can be exploited without any interaction from any user.
Scope: Unchanged: An exploited vulnerability can only affect resources managed by the same security authority. In this case, the vulnerable component and the impacted component are either the same, or both are managed by the same security authority.
Confidentiality: Low: There is some loss of confidentiality. Access to some restricted information is obtained, but the attacker does not have control over what information is obtained, or the amount or kind of loss is limited. The information disclosure does not cause a direct, serious loss to the impacted component.
Integrity: High: There is a total loss of integrity, or a complete loss of protection. For example, the attacker is able to modify any/all files protected by the impacted component. Alternatively, only some files can be modified, but malicious modification would present a direct, serious consequence to the impacted component.
Availability: Low: Performance is reduced or there are interruptions in resource availability. Even if repeated exploitation of the vulnerability is possible, the attacker does not have the ability to completely deny service to legitimate users. The resources in the impacted component are either partially available all of the time, or fully available only some of the time, but overall there is no direct, serious consequence to the impacted component.

Definitions: FIRST CVSS v3.1 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 8 May 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponised: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by 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 26 Oct 2026.

Disclosed: The CVE record is public on cve.org. Its publication is t = 0.
Detectable: A public nuclei template can find exposed instances, for defenders and attackers alike.
Weaponised: Public exploit code exists in Metasploit or Exploit-DB, or CISA SSVC or the CVSS exploit maturity reports a public proof of concept.
Exploited in the wild: CISA KEV lists it, CISA SSVC rates exploitation active, or a source reports attacks.
Observed by OffSeq Mirage: OffSeq Mirage honeypot sensors recorded attack traffic for this CVE, or found exposed hosts without attack traffic.

Moments are spaced evenly, not to scale; a dashed line marks a gap of six months or more. Deltas count from t = 0. Sources that give only a date (CISA KEV, Exploit-DB, or a time of exactly 00:00Z) read “same day” rather than hours. Metasploit modules carry the flaw’s disclosure date, not their release date, and nuclei templates carry no date, so both appear above but not on the timeline.

What to do

Upgrade praisonaiagents to 1.6.37; PraisonAI to 4.6.37.

Affected software

Product	Affected	Fixed in
PyPIpraisonaiagents	Affected <1.6.37	Fixed in 1.6.37
PyPIPraisonAI	Affected <4.6.37	Fixed in 4.6.37

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

AI-suggested

A patch is available in praisonaiagents version 1.6.37 and PraisonAI version 4.6.37 that addresses this issue. Users should upgrade to these fixed versions or later. Until patched, configuring the agent with a non-null _perm_allow list to explicitly restrict allowed tools can mitigate the risk by enforcing a declared-tool allowlist.

Description

The praisonaiagents package contains a vulnerability in its tool execution mechanism where undeclared tool names are resolved against global and __main__ module callables without proper permission checks. By default, the agent's permission allowlist is disabled, allowing attackers who can influence tool-call names to invoke unintended application functions that were never declared as tools. This can lead to unauthorized code execution.

Impact

An attacker able to influence tool-call names can execute arbitrary callables in the global or __main__ namespace that were never declared as tools, potentially leading to unauthorized code execution with the privileges of the agent process. This can compromise confidentiality, integrity, and availability of the affected system.

Summary

praisonaiagents resolves tool names first against declared tools and a registry, but if unresolved, it falls back to globals() and then the __main__ module to find a callable. The permission gate only rejects tool calls if a non-null allowlist (_perm_allow) is set; by default, _perm_allow is None, meaning all tools, including undeclared ones, are allowed. This allows an attacker controlling tool-call names to execute arbitrary callables defined in __main__ or globals, bypassing intended restrictions. The vulnerability was verified on version 1.6.35 of praisonaiagents and 4.6.35 of PraisonAI, with a fix introduced in versions 1.6.37 and 4.6.37.

CWE-470Use of Externally-Controlled Input to Select Classes or Code ('Unsafe Reflection') (opens in a new tab)
Base weaknessOWASP Top 10 A05:2025: Injection (opens in a new tab)
The product uses external input with reflection to select which classes or code to use, but it does not sufficiently prevent the input from selecting improper classes or code.
Architecture and Design
Refactor your code to avoid using reflection.
Architecture and Design
Do not use user-controlled inputs to select and load classes or code.
Implementation
Apply strict input validation by using allowlists or indirect selection to ensure that the user is only selecting allowable classes or code.
OWASP Cheat Sheets
XML Security (opens in a new tab)
Mass Assignment (opens in a new tab)
Injection Prevention (opens in a new tab)
SQL Injection Prevention (opens in a new tab)
Injection Prevention in Java (opens in a new tab)
OWASP ASVS 4.0.3
V13.3.1 (opens in a new tab)
V5.1.4 (opens in a new tab)
V5.1.3 (opens in a new tab)
Attack patterns
Reflection Injection (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 27 Oct 2026, 00:58 UTC

WeaknessesCWE-470

Technical details

References

Community reviews

Related threats