CVE-2026-40156

Summary

PraisonAI is a multi-agent teams system. Prior to 4.5.128, PraisonAI automatically loads a file named tools.py from the current working directory to discover and register custom agent tools. This loading process uses importlib.util.spec_from_file_location and immediately executes module-level code via spec.loader.exec_module() without explicit user consent, validation, or sandboxing. The tools.py file is loaded implicitly, even when it is not referenced in configuration files or explicitly requested by the user. As a result, merely placing a file named tools.py in the working directory is sufficient to trigger code execution. This behavior violates the expected security boundary between user-controlled project files (e.g., YAML configurations) and executable code, as untrusted content in the working directory is treated as trusted and executed automatically. If an attacker can place a malicious tools.py file into a directory where a user or automated system (e.g., CI/CD pipeline) runs praisonai, arbitrary code execution occurs immediately upon startup, before any agent logic begins. This vulnerability is fixed in 4.5.128.

Affected Software

Weaknesses

• CWE-94: CWE-94: Improper Control of Generation of Code ('Code Injection')
• CWE-426: CWE-426: Untrusted Search Path
• CWE-829: CWE-829: Inclusion of Functionality from Untrusted Control Sphere

ADP Enrichment

CISA ADP Vulnrichment

• SSVC:
• Exploitation: poc
  • Automatable: no
  • Technical Impact: total

Additional References

• https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-2g3w-cpc4-chr4

References

• https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-2g3w-cpc4-chr4

• ←Previous
• Next→