{"id":"CVE-2026-55522","state":"PUBLISHED","title":"PraisonAI workflow include bypasses tools.py autoload opt-in and executes included recipe code","description":"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() 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.","publishedAt":"2026-08-05T19:01:43.051Z","updatedAt":"2026-08-06T18:45:05.648Z","severity":{"score":7.8,"label":"High","version":"3.1","vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","source":"GitHub_M"},"assigner":"GitHub_M","products":["MervinPraison PraisonAI","MervinPraison praisonaiagents"],"affected":[{"vendor":"MervinPraison","product":"PraisonAI","versions":[{"version":">= 3.9.26, < 4.6.58","status":"affected"}]},{"vendor":"MervinPraison","product":"praisonaiagents","versions":[{"version":">= 0.12.12, < 1.6.58","status":"affected"}]}],"references":["https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hxmv-c4g6-5fqc"],"weaknesses":["CWE-94","CWE-426","CWE-829"],"ingestedAt":"2026-10-29T20:12:24.861Z","source":{"repository":"CVEProject/cvelistV5","path":"cves/2026/55xxx/CVE-2026-55522.json","commit":"556c9d3a8cd17e218bb8e452ba7cd619a384ff47"},"raw":{"dataType":"CVE_RECORD","dataVersion":"5.2","cveMetadata":{"cveId":"CVE-2026-55522","state":"PUBLISHED","datePublished":"2026-08-05T19:01:43.051Z","dateUpdated":"2026-08-06T18:45:05.648Z","assignerShortName":"GitHub_M","assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","dateReserved":"2026-06-16T22:44:22.284Z"},"containers":{"cna":{"title":"PraisonAI workflow include bypasses tools.py autoload opt-in and executes included recipe code","descriptions":[{"lang":"en","value":"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() 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."}],"affected":[{"vendor":"MervinPraison","product":"PraisonAI","versions":[{"version":">= 3.9.26, < 4.6.58","status":"affected"}]},{"vendor":"MervinPraison","product":"praisonaiagents","versions":[{"version":">= 0.12.12, < 1.6.58","status":"affected"}]}],"references":[{"url":"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hxmv-c4g6-5fqc","name":"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hxmv-c4g6-5fqc","tags":["x_refsource_CONFIRM"]}],"metrics":[{"cvssV3_1":{"attackComplexity":"LOW","attackVector":"LOCAL","availabilityImpact":"HIGH","baseScore":7.8,"baseSeverity":"HIGH","confidentialityImpact":"HIGH","integrityImpact":"HIGH","privilegesRequired":"NONE","scope":"UNCHANGED","userInteraction":"REQUIRED","vectorString":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","version":"3.1"}}],"problemTypes":[{"descriptions":[{"cweId":"CWE-94","lang":"en","description":"CWE-94: Improper Control of Generation of Code ('Code Injection')","type":"CWE"}]},{"descriptions":[{"cweId":"CWE-426","lang":"en","description":"CWE-426: Untrusted Search Path","type":"CWE"}]},{"descriptions":[{"cweId":"CWE-829","lang":"en","description":"CWE-829: Inclusion of Functionality from Untrusted Control Sphere","type":"CWE"}]}],"providerMetadata":{"shortName":"GitHub_M","orgId":"a0819718-46f1-4df5-94e2-005712e83aaa","dateUpdated":"2026-08-05T19:01:43.051Z"},"source":{"advisory":"GHSA-hxmv-c4g6-5fqc","discovery":"UNKNOWN"}},"adp":[{"title":"CISA ADP Vulnrichment","references":[{"url":"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hxmv-c4g6-5fqc","tags":["exploit"]}],"metrics":[{"other":{"type":"ssvc","content":{"timestamp":"2026-08-06T18:43:28.382511Z","id":"CVE-2026-55522","options":[{"Exploitation":"poc"},{"Automatable":"no"},{"Technical Impact":"total"}],"role":"CISA Coordinator","version":"2.0.3"}}}],"providerMetadata":{"shortName":"CISA-ADP","orgId":"134c704f-9b21-4f2e-91b3-4a467353bcc0","dateUpdated":"2026-08-06T18:45:05.648Z"}}]}}}