Authenticated command execution via unescaped template expressions
Published Apr 8, 2026 · Updated Apr 8, 2026
Code injection in PraisonAI before 4.5.115 allows remote authenticated users to execute system commands through crafted agent instructions. create_agent_centric_tools() returns tools such as acp_create_file that render unescaped content from agent.start() as template expressions instead of literal text. Exploitation requires access to submit agent instructions to an ACP-enabled runtime using automatic approvals, and commands run with the PraisonAI process privileges.
Summary
What happened
Code injection in PraisonAI before 4.5.115 allows remote authenticated users to execute system commands through crafted agent instructions. create_agent_centric_tools() returns tools such as acp_create_file that render unescaped content from agent.start() as template expressions instead of literal text. Exploitation requires access to submit agent instructions to an ACP-enabled runtime using automatic approvals, and commands run with the PraisonAI process privileges.
The record
- CVE
- CVE-2026-39891
- Published
- Apr 8, 2026
- Updated
- Apr 8, 2026
- Vendor
- Mervin Praison
- Product
- PraisonAI
- Classifications
- CWE-94, T1059
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Apr 8, 2026CVE publishedPublication date reported by the CVE source.
- Apr 8, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 4.5.115
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- GHSA-hwg5-x759-7wjg template-injection proof of conceptproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo