CVE 検索
公開されているすべての CVE とオープンソースのセキュリティアドバイザリ（NVD、OSV、GitHub）を、CVSS、EPSS、実際に悪用されているか（CISA KEV）とともに掲載しています。数時間ごとに更新されます。スキャンでは、検出した技術とこれらを照合します。
公開されているすべての CVE とオープンソースのセキュリティアドバイザリ（NVD、OSV、GitHub）を、CVSS、EPSS、実際に悪用されているか（CISA KEV）とともに掲載しています。数時間ごとに更新されます。スキャンでは、検出した技術とこれらを照合します。
| 14/09/2026 |
| CVE-2026-56839 | 高7.3 | PraisonAI is a multi-agent teams system. Prior to 4.6.59, the CODE_TOOLS wrappers keep _workspace_root as None and pass workspace=None to read_file, search_replace, and apply_diff helpers that enforce path containment only for a truthy workspace. An application that exposes code_read_file, code_search_replace, or code_ | 14/09/2026 |
| CVE-2026-57125 | 緊急9.8 | PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.59 and praisonaiagents 1.6.59, the unauthenticated POST /api/v1/runs Jobs API accepts attacker-controlled agent_yaml, and the approve field can mark execute_command as YAML-approved before @require_approval checks critical tools. This chain allows a remote | 14/09/2026 |
| CVE-2026-55539 | 高8.6 | PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.51, the Jobs API create_app function mounts /api/v1/runs without authentication. Any reachable caller can submit jobs, read results, cancel runs, or delete jobs using operator credentials. The fix adds PRAISONAI_JOBS_API_KEY middleware for Authorization or | 25/08/2026 |
| CVE-2026-55536 | 緊急9.1 | PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, Browser Server _handle_connection() checks Chrome extension origins with re.match() and the unanchored expression chrome-extension://[a-z0-9]{32}. Extra trailing characters pass before websocket.accept(), allowing start_session commands and unauthorize | 25/08/2026 |
| CVE-2026-55533 | 高8.2 | PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, create_auth_middleware() allows requests when auth=api-key lacks PRAISONAI_API_KEY or JWT authentication lacks PRAISONAI_JWT_SECRET. An externally bound Recipe server can therefore accept unauthenticated POST /v1/recipes/run requests despite authentica | 25/08/2026 |
| CVE-2026-55532 | 高7.6 | PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, MCP HTTP Stream _validate_origin uses request_origin.startswith(allowed), allowing the attacker-controlled localhost.attacker.com HTTP origin to satisfy the localhost allowlist. A webpage can send Content-Type: text/plain requests without preflight and | 25/08/2026 |
| CVE-2026-55541 | 高8.8 | PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, praisonai serve agents and praisonai serve unified parse --api-key but _create_agents_app() and _create_unified_app() do not install a credential check. Unauthenticated callers can reach POST /agents and POST /api/v1/agents/{id}/invoke. This issue is f | 25/08/2026 |
| CVE-2026-55540 | 高7.1 | PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.51, is_path_within_directory() uses os.path.abspath() rather than os.path.realpath() for the workspace boundary. A symlink inside workspace can point outside and still pass the check, allowing read_file and other code tools to access files outside the conf | 25/08/2026 |
| CVE-2026-55538 | 高7.3 | PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.51, praisonai serve agents parses config["api_key"] but _create_agents_app() does not authenticate POST /agents or POST /agents/{agent_name}. Missing or incorrect bearer and X-API-Key values still reach agent execution. This issue is fixed in version 4.6.5 | 25/08/2026 |
| CVE-2026-55537 | 高7.1 | PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, JobSubmitRequest.validate_webhook_url() accepts webhook_url when resolution raises socket.gaierror because the exception path uses except socket.gaierror: pass. JobExecutor._send_webhook() later performs a fresh lookup, allowing DNS changes to direct t | 25/08/2026 |
| CVE-2026-55535 | 中6.8 | PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the Jobs API validate_webhook_url() path fails open on socket.gaierror and does not bind the validated address to the later request. An attacker webhook_url can later resolve to 127.0.0.1, 169.254.169.254, or another internal address. This issue is fix | 25/08/2026 |
| CVE-2026-55534 | 高8.6 | PraisonAI is a multi-agent teams system. From praisonai 4.6.34 until 4.6.58, praisonai serve agents accepts --api-key but _create_agents_app() does not authenticate POST /agents or POST /agents/{agent_name}. A network caller can invoke configured agents without credentials even when an API key was supplied. This issue | 25/08/2026 |
| CVE-2026-55531 | 中6.5 | PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the MCP HTTP Stream mcp_post handler creates a new _sessions entry for every initialize request but does not call _cleanup_sessions or enforce a maximum. An unauthenticated caller can exhaust memory. The fix invokes cleanup and limits sessions through | 25/08/2026 |
| CVE-2026-55529 | 中6.9 | PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, the MCP HTTP Stream _validate_origin method accepts request_origin.startswith(allowed), so the attacker-controlled localhost.evil.example HTTP origin matches the localhost allowlist. Without an API key, a malicious webpage can submit tools/call request | 25/08/2026 |
| CVE-2026-55522 | 高7.8 | 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_fro | 05/08/2026 |
| CVE-2026-47398 | 高8.1 | PraisonAI is a multi-agent teams system. The v4.6.32 chokepoint refactor (which patched CVE-2026-44334 / GHSA-xcmw-grxf-wjhj) added the PRAISONAI_ALLOW_LOCAL_TOOLS env-var gate to the tool_override.py sinks. However, two additional spec.loader.exec_module call sites in praisonai/agents_generator.py were missed and rema | 21/07/2026 |
| CVE-2026-47397 | 高7.1 | PraisonAI is a multi-agent teams system. Prior to version 4.6.40, hidden metadata in a webpage causes PraisonAI agents to write attacker-controlled content to arbitrary paths. `write_file` skips path validation when `workspace=None` (always `None` in production). Version 4.6.40 fixes the issue. | 21/07/2026 |