{"id":"CVE-2026-55522","title":"PraisonAI is a multi-agent teams system","summary":"PraisonAI is a multi-agent teams system. In versions 3.9.26 through 4.6.57 of praiseonai and 0.12.12 through 1.6.57 of praiseonaiagents, the workflow \"include\" feature is vulnerable to code execution. Workflow._execute_include() implicit…","severity":"high","cvss":7.8,"cvssVector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","cwe":["CWE-94","CWE-426","CWE-829"],"vendor":"praisonaiagents","product":"praisonaiagents","affected":["praisonaiagents >= 0.12.12, < 1.6.58","PraisonAI >= 3.9.26, < 4.6.58"],"patched":["praisonaiagents 1.6.58","PraisonAI 4.6.58"],"published":"2026-08-05","updated":"2026-09-08","sourceUpdated":"2026-09-08T20:51:43.490","source":"NVD","sourceUrl":"https://nvd.nist.gov/vuln/detail/CVE-2026-55522","references":[{"url":"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hxmv-c4g6-5fqc","label":"security-advisories@github.com"},{"url":"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hxmv-c4g6-5fqc","label":"134c704f-9b21-4f2e-91b3-4a467353bcc0"},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-55522"},{"url":"https://github.com/MervinPraison/PraisonAI/commit/2f9677abb2ea68eab864ee8b6a828fd0141612e1"},{"url":"https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.58"},{"url":"https://github.com/advisories/GHSA-hxmv-c4g6-5fqc"},{"url":"https://github.com/MervinPraison/PraisonAI"},{"url":"https://pypi.org/project/praisonai"},{"url":"https://pypi.org/project/praisonaiagents"}],"tags":["nvd","ghsa","pip","osv"],"epss":0.00152,"epssPercentile":0.04726,"aliases":["GHSA-hxmv-c4g6-5fqc","PYSEC-2026-3891","PYSEC-2026-3903"],"ecosystem":"pip","ingestedAt":"2026-08-25T14:27:02.715Z","slug":"CVE-2026-55522","body":"## Overview\n\nPraisonAI is a multi-agent teams system. In versions 3.9.26 through 4.6.57 of praiseonai and 0.12.12 through 1.6.57 of praiseonaiagents, the workflow \"include\" feature is vulnerable to code execution. Workflow._execute_include() implicitly imports and runs an included recipe's tools.py via a raw importlib.util.spec_from_file_location() and spec.loader.exec_module() call, without honoring the PRAISONAI_ALLOW_TEMPLATE_TOOLS/PRAISONAI_ALLOW_LOCAL_TOOLS autoload opt-in gates or routing through the centralized safe loader that protects the other tools.py autoload paths. As a result, a workflow that includes an attacker-controlled local recipe directory executes arbitrary module-level Python code during include setup, before any child workflow parsing or model call, and the same sink is reachable through the higher-level praisonai.recipe.run() recipe API. An attacker who can cause a victim process to run a workflow or recipe that includes an untrusted local recipe achieves arbitrary Python code execution as the PraisonAI process user, a variant that bypasses the hardening applied to the previously disclosed automatic tools.py RCE advisory family. This issue has been fixed in version 4.6.58 of praisonai and 1.6.58 of praisonaiagents.\n\n## Remediation\n\nRefer to the linked advisories for vendor-supplied fixes and affected version ranges.\n\n## Package advisory (CVE-2026-55522)\n\nAffected packages:\n\n- `praisonaiagents >= 0.12.12, < 1.6.58`\n- `PraisonAI >= 3.9.26, < 4.6.58`\n\nPatched in:\n\n- `praisonaiagents 1.6.58`\n- `PraisonAI 4.6.58`\n\nSource: https://github.com/advisories/GHSA-hxmv-c4g6-5fqc","depth":"twilight","depthScore":43,"depthScoreParts":{"impact":42.9,"likelihood":0,"exploitation":0,"ransomware":0},"changes":[]}