CVE-2026-39891 | MervinPraison PraisonAI up to 4.5.114 File Content create_agent_centric_tools code injection (GHSA-hwg5-x759-7wjg)

VDB-356488 · CVE-2026-39891 · GHSA-HWG5-X759-7WJG MERVINPRAISON PRAISONAI UP TO 4.5.114 FILE CONTENT CREATE_AGENT_CENTRIC_TOOLS CODE INJECTION HISTORYDIFFRELATEJSONXMLCTI CVSS Meta Temp Score Current Exploit Price (≈) CTI Interest Score 7.4 $0-$5k 0.80+ Summaryinfo A vulnerability was found in MervinPraison PraisonAI up to 4.5.114. It has been declared as critical. Affected by this vulnerability is the function create_agent_centric_tools of the component File Content Handler. Executing a manipulation can lead to code injection. This vulnerability appears as CVE-2026-39891. The attack may be performed from remote. There is no available exploit. It is recommended to upgrade the affected component. Detailsinfo A vulnerability was found in MervinPraison PraisonAI up to 4.5.114. It has been declared as critical. This vulnerability affects the function create_agent_centric_tools of the component File Content Handler. The manipulation with an unknown input leads to a code injection vulnerability. The CWE definition for the vulnerability is CWE-94. The product constructs all or part of a code segment using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the syntax or behavior of the intended code segment. As an impact it is known to affect confidentiality, integrity, and availability. CVE summarizes: PraisonAI is a multi-agent teams system. Prior to 4.5.115, the create_agent_centric_tools() function returns tools (like acp_create_file) that process file content using template rendering. When user input from agent.start() is passed directly into these tools without escaping, template expressions in the input are executed rather than treated as literal text. This vulnerability is fixed in 4.5.115. The advisory is shared for download at github.com. This vulnerability was named CVE-2026-39891 since 04/07/2026. The exploitation appears to be easy. The attack can be initiated remotely. There are known technical details, but no exploit is available. The MITRE ATT&CK project declares the attack technique as T1059. Upgrading to version 4.5.115 eliminates this vulnerability. Productinfo Vendor MervinPraison Name PraisonAI Version 4.5.114 Website Product: https://github.com/MervinPraison/PraisonAI/ CPE 2.3info 🔒 CPE 2.2info 🔒 CVSSv4info VulDB Vector: 🔒 VulDB Reliability: 🔍 CVSSv3info VulDB Meta Base Score: 7.6 VulDB Meta Temp Score: 7.4 VulDB Base Score: 6.3 VulDB Temp Score: 6.0 VulDB Vector: 🔒 VulDB Reliability: 🔍 CNA Base Score: 8.8 CNA Vector (GitHub_M): 🔒 CVSSv2info Vector Complexity Authentication Confidentiality Integrity Availability Unlock Unlock Unlock Unlock Unlock Unlock Unlock Unlock Unlock Unlock Unlock Unlock Unlock Unlock Unlock Unlock Unlock Unlock VulDB Base Score: 🔒 VulDB Temp Score: 🔒 VulDB Reliability: 🔍 Exploitinginfo Class: Code injection CWE: CWE-94 / CWE-74 / CWE-707 CAPEC: 🔒 ATT&CK: 🔒 Physical: No Local: No Remote: Yes Availability: 🔒 Status: Not defined Price Prediction: 🔍 Current Price Estimation: 🔒 0-Day Unlock Unlock Unlock Unlock Today Unlock Unlock Unlock Unlock Threat Intelligenceinfo Interest: 🔍 Active Actors: 🔍 Active APT Groups: 🔍 Countermeasuresinfo Recommended: Upgrade Status: 🔍 0-Day Time: 🔒 Upgrade: PraisonAI 4.5.115 Timelineinfo 04/07/2026 CVE reserved 04/09/2026 +2 days Advisory disclosed 04/09/2026 +0 days VulDB entry created 04/09/2026 +0 days VulDB entry last update Sourcesinfo Product: github.com Advisory: GHSA-hwg5-x759-7wjg Status: Confirmed CVE: CVE-2026-39891 (🔒) GCVE (CVE): GCVE-0-2026-39891 GCVE (VulDB): GCVE-100-356488 Entryinfo Created: 04/09/2026 02:48 Changes: 04/09/2026 02:48 (66) Complete: 🔍 Cache ID: 99:0CA:101 Discussion No comments yet. Languages: en. Please log in to comment. ◂ PreviousOverviewNext ▸