High severity · published Apr 8, 2026
CVE-2026-39891
PraisonAI has a Template Injection in Agent Tool Definitions
8.8
CVSS
0.6%
EPSS
No
On KEV
Description
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.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Attack vector
Network
Complexity
Low
Privileges
Low
User interaction
None
Confidentiality
High
Integrity
High
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.6% · higher than 46% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
PR
PraisonAI · MervinPraison
< 4.5.115 · source: vendor, NVD
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-39891
CVE.org
https://www.cve.org/CVERecord?id=CVE-2026-39891
Exploit
https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hwg5-x759-7wjg
More from PraisonAI
10.0
CVE-2026-48168
PraisonAI: GitHub Actions Claude workflow command injection via unquoted PR branch name
10.0
CVE-2026-61447
PraisonAI before 1.6.78 Remote Code Execution via CodeAgent
10.0
CVE-2026-40114
PraisonAI has Server-Side Request Forgery via Unvalidated webhook_url in Jobs API
10.0
CVE-2026-39305
Arbitrary File Write / Path Traversal in Action Orchestrator
10.0
CVE-2026-34955
PraisonAI: Sandbox Escape via shell=True and Bypassable Blocklist in SubprocessSandbox