{"api_version":"1","generated_at":"2026-05-08T15:54:34+00:00","cve":"CVE-2026-44336","urls":{"html":"https://cve.report/CVE-2026-44336","api":"https://cve.report/api/cve/CVE-2026-44336.json","docs":"https://cve.report/api","cve_org":"https://www.cve.org/CVERecord?id=CVE-2026-44336","nvd":"https://nvd.nist.gov/vuln/detail/CVE-2026-44336"},"summary":{"title":"PraisonAI MCP `tools/call` path-traversal and RCE via Python `.pth` injection","description":"PraisonAI is a multi-agent teams system. Prior to version 4.6.34, PraisonAI's MCP (Model Context Protocol) server (praisonai mcp serve) registers four file-handling tools by default — praisonai.rules.create, praisonai.rules.show, praisonai.rules.delete, and praisonai.workflow.show. Each accepts a path or filename string from MCP tools/call arguments and joins it onto ~/.praison/rules/ (or, for workflow.show, accepts an absolute path) with no containment check. The JSON-RPC dispatcher passes params[\"arguments\"] blind to each handler via **kwargs without validating against the advertised input schema. By setting rule_name=\"../../<some-path>\" an attacker walks out of the rules directory and writes any file the running user can write. Dropping a Python .pth file into the user site-packages directory escalates this primitive to arbitrary code execution in any subsequent Python process the user spawns — the next praisonai CLI invocation, an IDE script run, the user's python REPL, or any background Python service. This issue has been patched in version 4.6.34.","state":"PUBLISHED","assigner":"GitHub_M","published_at":"2026-05-08 14:16:46","updated_at":"2026-05-08 14:16:46"},"problem_types":["CWE-20","CWE-22","CWE-94","CWE-829","CWE-913","CWE-20 CWE-20: Improper Input Validation","CWE-22 CWE-22: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')","CWE-94 CWE-94: Improper Control of Generation of Code ('Code Injection')","CWE-829 CWE-829: Inclusion of Functionality from Untrusted Control Sphere","CWE-913 CWE-913: Improper Control of Dynamically-Managed Code Resources"],"metrics":[{"version":"4.0","source":"security-advisories@github.com","type":"Secondary","score":"9.4","severity":"CRITICAL","vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X","data":{"version":"4.0","vectorString":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X","baseScore":9.4,"baseSeverity":"CRITICAL","attackVector":"NETWORK","attackComplexity":"LOW","attackRequirements":"NONE","privilegesRequired":"NONE","userInteraction":"PASSIVE","vulnConfidentialityImpact":"HIGH","vulnIntegrityImpact":"HIGH","vulnAvailabilityImpact":"HIGH","subConfidentialityImpact":"HIGH","subIntegrityImpact":"HIGH","subAvailabilityImpact":"HIGH","exploitMaturity":"NOT_DEFINED","confidentialityRequirement":"NOT_DEFINED","integrityRequirement":"NOT_DEFINED","availabilityRequirement":"NOT_DEFINED","modifiedAttackVector":"NOT_DEFINED","modifiedAttackComplexity":"NOT_DEFINED","modifiedAttackRequirements":"NOT_DEFINED","modifiedPrivilegesRequired":"NOT_DEFINED","modifiedUserInteraction":"NOT_DEFINED","modifiedVulnConfidentialityImpact":"NOT_DEFINED","modifiedVulnIntegrityImpact":"NOT_DEFINED","modifiedVulnAvailabilityImpact":"NOT_DEFINED","modifiedSubConfidentialityImpact":"NOT_DEFINED","modifiedSubIntegrityImpact":"NOT_DEFINED","modifiedSubAvailabilityImpact":"NOT_DEFINED","Safety":"NOT_DEFINED","Automatable":"NOT_DEFINED","Recovery":"NOT_DEFINED","valueDensity":"NOT_DEFINED","vulnerabilityResponseEffort":"NOT_DEFINED","providerUrgency":"NOT_DEFINED"}},{"version":"4.0","source":"CNA","type":"DECLARED","score":"9.4","severity":"CRITICAL","vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H","data":{"attackComplexity":"LOW","attackRequirements":"NONE","attackVector":"NETWORK","baseScore":9.4,"baseSeverity":"CRITICAL","privilegesRequired":"NONE","subAvailabilityImpact":"HIGH","subConfidentialityImpact":"HIGH","subIntegrityImpact":"HIGH","userInteraction":"PASSIVE","vectorString":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H","version":"4.0","vulnAvailabilityImpact":"HIGH","vulnConfidentialityImpact":"HIGH","vulnIntegrityImpact":"HIGH"}}],"references":[{"url":"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9mqq-jqxf-grvw","name":"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9mqq-jqxf-grvw","refsource":"security-advisories@github.com","tags":[],"title":"","mime":"","httpstatus":"","archivestatus":"0"},{"url":"https://www.cve.org/CVERecord?id=CVE-2026-44336","name":"CVE Program record","refsource":"CVE.ORG","tags":["canonical"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-44336","name":"NVD vulnerability detail","refsource":"NVD","tags":["canonical","analysis"]}],"affected":[{"source":"CNA","vendor":"MervinPraison","product":"PraisonAI","version":"affected < 4.6.34","platforms":[]}],"timeline":[],"solutions":[],"workarounds":[],"exploits":[],"credits":[],"nvd_cpes":[],"vendor_comments":[],"enrichments":{"kev":null,"epss":null,"legacy_qids":[]},"source_records":{"cve_program":{"containers":{"cna":{"affected":[{"product":"PraisonAI","vendor":"MervinPraison","versions":[{"status":"affected","version":"< 4.6.34"}]}],"descriptions":[{"lang":"en","value":"PraisonAI is a multi-agent teams system. Prior to version 4.6.34, PraisonAI's MCP (Model Context Protocol) server (praisonai mcp serve) registers four file-handling tools by default — praisonai.rules.create, praisonai.rules.show, praisonai.rules.delete, and praisonai.workflow.show. Each accepts a path or filename string from MCP tools/call arguments and joins it onto ~/.praison/rules/ (or, for workflow.show, accepts an absolute path) with no containment check. The JSON-RPC dispatcher passes params[\"arguments\"] blind to each handler via **kwargs without validating against the advertised input schema. By setting rule_name=\"../../<some-path>\" an attacker walks out of the rules directory and writes any file the running user can write. Dropping a Python .pth file into the user site-packages directory escalates this primitive to arbitrary code execution in any subsequent Python process the user spawns — the next praisonai CLI invocation, an IDE script run, the user's python REPL, or any background Python service. This issue has been patched in version 4.6.34."}],"metrics":[{"cvssV4_0":{"attackComplexity":"LOW","attackRequirements":"NONE","attackVector":"NETWORK","baseScore":9.4,"baseSeverity":"CRITICAL","privilegesRequired":"NONE","subAvailabilityImpact":"HIGH","subConfidentialityImpact":"HIGH","subIntegrityImpact":"HIGH","userInteraction":"PASSIVE","vectorString":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H","version":"4.0","vulnAvailabilityImpact":"HIGH","vulnConfidentialityImpact":"HIGH","vulnIntegrityImpact":"HIGH"}}],"problemTypes":[{"descriptions":[{"cweId":"CWE-20","description":"CWE-20: Improper Input Validation","lang":"en","type":"CWE"}]},{"descriptions":[{"cweId":"CWE-22","description":"CWE-22: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')","lang":"en","type":"CWE"}]},{"descriptions":[{"cweId":"CWE-94","description":"CWE-94: Improper Control of Generation of Code ('Code Injection')","lang":"en","type":"CWE"}]},{"descriptions":[{"cweId":"CWE-829","description":"CWE-829: Inclusion of Functionality from Untrusted Control Sphere","lang":"en","type":"CWE"}]},{"descriptions":[{"cweId":"CWE-913","description":"CWE-913: Improper Control of Dynamically-Managed Code Resources","lang":"en","type":"CWE"}]}],"providerMetadata":{"dateUpdated":"2026-05-08T13:32:33.605Z","orgId":"a0819718-46f1-4df5-94e2-005712e83aaa","shortName":"GitHub_M"},"references":[{"name":"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9mqq-jqxf-grvw","tags":["x_refsource_CONFIRM"],"url":"https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9mqq-jqxf-grvw"}],"source":{"advisory":"GHSA-9mqq-jqxf-grvw","discovery":"UNKNOWN"},"title":"PraisonAI MCP `tools/call` path-traversal and RCE via Python `.pth` injection"}},"cveMetadata":{"assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","assignerShortName":"GitHub_M","cveId":"CVE-2026-44336","datePublished":"2026-05-08T13:32:33.605Z","dateReserved":"2026-05-05T19:52:59.147Z","dateUpdated":"2026-05-08T13:32:33.605Z","state":"PUBLISHED"},"dataType":"CVE_RECORD","dataVersion":"5.2"},"nvd":{"publishedDate":"2026-05-08 14:16:46","lastModifiedDate":"2026-05-08 14:16:46","problem_types":["CWE-20","CWE-22","CWE-94","CWE-829","CWE-913","CWE-20 CWE-20: Improper Input Validation","CWE-22 CWE-22: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')","CWE-94 CWE-94: Improper Control of Generation of Code ('Code Injection')","CWE-829 CWE-829: Inclusion of Functionality from Untrusted Control Sphere","CWE-913 CWE-913: Improper Control of Dynamically-Managed Code Resources"],"metrics":{"cvssMetricV40":[{"source":"security-advisories@github.com","type":"Secondary","cvssData":{"version":"4.0","vectorString":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X","baseScore":9.4,"baseSeverity":"CRITICAL","attackVector":"NETWORK","attackComplexity":"LOW","attackRequirements":"NONE","privilegesRequired":"NONE","userInteraction":"PASSIVE","vulnConfidentialityImpact":"HIGH","vulnIntegrityImpact":"HIGH","vulnAvailabilityImpact":"HIGH","subConfidentialityImpact":"HIGH","subIntegrityImpact":"HIGH","subAvailabilityImpact":"HIGH","exploitMaturity":"NOT_DEFINED","confidentialityRequirement":"NOT_DEFINED","integrityRequirement":"NOT_DEFINED","availabilityRequirement":"NOT_DEFINED","modifiedAttackVector":"NOT_DEFINED","modifiedAttackComplexity":"NOT_DEFINED","modifiedAttackRequirements":"NOT_DEFINED","modifiedPrivilegesRequired":"NOT_DEFINED","modifiedUserInteraction":"NOT_DEFINED","modifiedVulnConfidentialityImpact":"NOT_DEFINED","modifiedVulnIntegrityImpact":"NOT_DEFINED","modifiedVulnAvailabilityImpact":"NOT_DEFINED","modifiedSubConfidentialityImpact":"NOT_DEFINED","modifiedSubIntegrityImpact":"NOT_DEFINED","modifiedSubAvailabilityImpact":"NOT_DEFINED","Safety":"NOT_DEFINED","Automatable":"NOT_DEFINED","Recovery":"NOT_DEFINED","valueDensity":"NOT_DEFINED","vulnerabilityResponseEffort":"NOT_DEFINED","providerUrgency":"NOT_DEFINED"}}]},"configurations":[]},"legacy_mitre":{"record":{"CveYear":"2026","CveId":"44336","Ordinal":"1","Title":"PraisonAI MCP `tools/call` path-traversal and RCE via Python `.p","CVE":"CVE-2026-44336","Year":"2026"},"notes":[{"CveYear":"2026","CveId":"44336","Ordinal":"1","NoteData":"PraisonAI is a multi-agent teams system. Prior to version 4.6.34, PraisonAI's MCP (Model Context Protocol) server (praisonai mcp serve) registers four file-handling tools by default — praisonai.rules.create, praisonai.rules.show, praisonai.rules.delete, and praisonai.workflow.show. Each accepts a path or filename string from MCP tools/call arguments and joins it onto ~/.praison/rules/ (or, for workflow.show, accepts an absolute path) with no containment check. The JSON-RPC dispatcher passes params[\"arguments\"] blind to each handler via **kwargs without validating against the advertised input schema. By setting rule_name=\"../../<some-path>\" an attacker walks out of the rules directory and writes any file the running user can write. Dropping a Python .pth file into the user site-packages directory escalates this primitive to arbitrary code execution in any subsequent Python process the user spawns — the next praisonai CLI invocation, an IDE script run, the user's python REPL, or any background Python service. This issue has been patched in version 4.6.34.","Type":"Description","Title":"PraisonAI MCP `tools/call` path-traversal and RCE via Python `.p"}]}}}