Unauthenticated code execution via unguarded recipe tools import
Published May 8, 2026 · Updated May 8, 2026
Code injection in PraisonAI 4.5.139 through 4.6.31 allows remote attackers to execute arbitrary code through a crafted recipe. The create_tool_registry_with_overrides path loads template-local tools.py with exec_module without an allowlist, signature check, or environment gate. Default unauthenticated recipe serving accepts local paths or GitHub recipes, so supplied Python runs in the server process before any agent step.
Summary
What happened
Code injection in PraisonAI 4.5.139 through 4.6.31 allows remote attackers to execute arbitrary code through a crafted recipe. The create_tool_registry_with_overrides path loads template-local tools.py with exec_module without an allowlist, signature check, or environment gate. Default unauthenticated recipe serving accepts local paths or GitHub recipes, so supplied Python runs in the server process before any agent step.
The record
- CVE
- CVE-2026-44334
- Published
- May 8, 2026
- Updated
- May 8, 2026
- Vendor
- PraisonAI
- Product
- PraisonAI
- Classifications
- CWE-94, T1190, T1059.006
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- May 8, 2026CVE publishedPublication date reported by the CVE source.
- May 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=>= 4.5.139, < 4.6.32
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-xcmw-grxf-wjhj recipe-run proof of conceptfunctional · 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