Arbitrary code execution via ungated recipe tool import
Published Aug 5, 2026 · Updated Aug 5, 2026
Code injection in PraisonAI 3.9.26 through 4.6.57 and praisonaiagents 0.12.12 through 1.6.57 lets attackers run code via a recipe. Workflow._execute_include() passes an included tools.py path to importlib.util.spec_from_file_location() and exec_module() without enforcing either autoload opt-in gate. Execution occurs as the PraisonAI process user before workflow parsing or a model call, after a victim process is induced to include an attacker-controlled local recipe.
Summary
What happened
Code injection in PraisonAI 3.9.26 through 4.6.57 and praisonaiagents 0.12.12 through 1.6.57 lets attackers run code via a recipe. Workflow._execute_include() passes an included tools.py path to importlib.util.spec_from_file_location() and exec_module() without enforcing either autoload opt-in gate. Execution occurs as the PraisonAI process user before workflow parsing or a model call, after a victim process is induced to include an attacker-controlled local recipe.
The record
- CVE
- CVE-2026-55522
- Published
- Aug 5, 2026
- Updated
- Aug 5, 2026
- Vendor
- Mervin Praison
- Product
- PraisonAI
- Classifications
- CWE-94, CWE-426, CWE-829, T1204.002, T1059.006
- Attack vector
- local
- Privileges
- unauthenticated
Timeline
How it unfolded
- Aug 5, 2026CVE publishedPublication date reported by the CVE source.
- Aug 5, 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=>= 3.9.26, < 4.6.58
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
- Workflow include local proof of vulnerabilityproof 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