CVE-2026-57148 | Critical | 9.8 | 2026-09-15 | PraisonAI is a multi-agent teams system. Prior to 0.1.6, praisonai_platform/services/auth_service.py falls back to the public dev-secret-change-me HS256 signin… |
CVE-2026-57147 | Critical | 9.8 | 2026-09-15 | PraisonAI is a multi-agent teams system. Prior to 0.1.6, praisonai_platform/services/auth_service.py assigns the public dev-secret-change-me value to JWT_SECRE… |
CVE-2026-57141 | Critical | 9.8 | 2026-09-15 | PraisonAI is a multi-agent teams system. Prior to 1.7.2, the codeMode tool in src/praisonai-ts/src/tools/builtins/code-mode.ts executes model-generated JavaScr… |
CVE-2026-57140 | Critical | 9.4 | 2026-09-15 | PraisonAI is a multi-agent teams system. From 1.6.0 until 1.7.2, AgentOS in src/praisonai-ts/src/os/agentos.ts uses the 0.0.0.0 default from src/praisonai-ts/s… |
CVE-2026-57139 | Critical | 9.8 | 2026-09-15 | PraisonAI is a multi-agent teams system. From 1.5.0 until 1.7.2, MCPServer.startHttp() in src/praisonai-ts/src/mcp/server.ts binds without a host restriction a… |
CVE-2026-57138 | Critical | 9.9 | 2026-09-15 | PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, codeMode in src/praisonai-ts/src/tools/builtins/code-mode.ts executes untrusted JavaScript wit… |
CVE-2026-57137 | High | 8.8 | 2026-09-15 | PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, createAgentLoop() in src/praisonai-ts/src/ai/agent-loop.ts passes executable tools to generate… |
CVE-2026-57136 | High | 8.8 | 2026-09-15 | PraisonAI is a multi-agent teams system. From 1.2.3 until 1.7.2, CommandValidator in src/praisonai-ts/src/cli/features/sandbox-executor.ts validates only the f… |
CVE-2026-57135 | High | 7.6 | 2026-09-15 | PraisonAI is a multi-agent teams system. From 1.2.3 until 1.7.2, SandboxExecutor network-isolated mode in src/praisonai-ts/src/cli/features/sandbox-executor.ts… |
CVE-2026-57134 | High | 8.2 | 2026-09-15 | PraisonAI is a multi-agent teams system. From 1.5.1 until 1.7.2, MCPSecurity.evaluatePolicy() in src/praisonai-ts/src/mcp/security.ts invokes the configured cr… |
CVE-2026-57133 | High | 8.8 | 2026-09-15 | PraisonAI is a multi-agent teams system. From 1.5.1 until 1.7.2, the shell() helper exported from src/praisonai-ts/src/tools/utility-tools.ts checks only the f… |
CVE-2026-57112 | High | 8.3 | 2026-09-15 | PraisonAI is a multi-agent teams system. From praisonaiagents 0.6.0 until 1.6.59 and PraisonAI 3.10.0 until 4.6.59, ToolsMCPServer.run_sse() in src/praisonai-a… |
CVE-2026-57145 | Critical | 9.1 | 2026-09-14 | PraisonAI is a multi-agent teams system. Prior to 4.6.62, src/praisonai/praisonai/tools/multiedit.py passes the LLM-controlled filepath parameter directly to o… |
CVE-2026-57132 | High | 8.2 | 2026-09-14 | PraisonAI is a multi-agent teams system. Prior to 4.6.62, setting PRAISONAI_CALL_AUTH to disabled makes verify_token accept requests to /api/v1/agents/{id}/inv… |
CVE-2026-57131 | Critical | 9.8 | 2026-09-14 | PraisonAI is a multi-agent teams system. Prior to 4.6.58, praisonai.jobs.server.create_app mounts praisonai.jobs.router.create_router under /api/v1/runs withou… |
CVE-2026-57127 | Critical | 9.8 | 2026-09-14 | PraisonAI is a multi-agent teams system. Prior to 4.6.58, recipe serve installs APIKeyAuthMiddleware or JWTAuthMiddleware when an operator selects api-key or J… |
CVE-2026-57124 | Critical | 9.8 | 2026-09-14 | PraisonAI is a multi-agent teams system. Prior to 4.6.59, the default UI host applications expose POST /api/mcp/connect without mandatory authentication and ac… |
CVE-2026-57122 | High | 8.6 | 2026-09-14 | PraisonAI is a multi-agent teams system. Prior to 4.6.59, the WhatsApp and Linear bot webhook handlers verify HMAC signatures only when WHATSAPP_APP_SECRET or… |
CVE-2026-57119 | High | 7.5 | 2026-09-14 | PraisonAI is a multi-agent teams system. Prior to 4.6.59, the unauthenticated Jobs API accepts an absolute or traversing agent_file path in POST /api/v1/runs a… |
CVE-2026-56839 | High | 7.3 | 2026-09-14 | 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_rep… |
CVE-2026-57130 | High | 8.1 | 2026-09-14 | PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, src/praisonai-agents/praisonaiagents/tools/email_tools.py interpolates LLM-controlled… |
CVE-2026-57129 | High | 7.5 | 2026-09-14 | PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, MentionsParser._process_file_mention accepts file-mention values and falls back from… |
CVE-2026-57128 | Medium | 4.3 | 2026-09-14 | PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.58, the SSE server in src/praisonai-agents/praisonaiagents/server/server.py does not cons… |
CVE-2026-57126 | High | 8.5 | 2026-09-14 | PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.58, SpiderTools._validate_url calls _host_is_blocked, which checks literal host encodings… |
CVE-2026-57125 | Critical | 9.8 | 2026-09-14 | 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-… |
CVE-2026-57123 | Critical | 9.8 | 2026-09-14 | PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, ToolsMCPServer.run_sse and launch_tools_mcp_server bind to 0.0.0.0 and create /sse an… |
CVE-2026-57120 | Medium | 6.5 | 2026-09-14 | PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, execute_code sandbox mode permits runtime assembly of blocklisted dunder names and al… |
CVE-2026-57115 | Medium | 6.5 | 2026-09-14 | PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, SpiderTools.scrape_page validates only the initial URL and lets requests.Session.get… |
CVE-2026-55539 | High | 8.6 | 2026-08-25 | 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… |
CVE-2026-55536 | Critical | 9.1 | 2026-08-25 | 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… |
CVE-2026-55533 | High | 8.2 | 2026-08-25 | 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 a… |
CVE-2026-55532 | High | 7.6 | 2026-08-25 | 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 atta… |
CVE-2026-55541 | | | 2026-08-25 | 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()… |
CVE-2026-55540 | High | 7.1 | 2026-08-25 | 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 wo… |
CVE-2026-55538 | High | 7.3 | 2026-08-25 | 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 authentic… |
CVE-2026-55537 | High | 7.1 | 2026-08-25 | PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.58, JobSubmitRequest.validate_webhook_url() accepts webhook_url when resolution raises socket.g… |
CVE-2026-55535 | Medium | 6.8 | 2026-08-25 | 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 th… |
CVE-2026-55534 | High | 8.6 | 2026-08-25 | 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 authent… |
CVE-2026-55531 | Medium | 6.5 | 2026-08-25 | 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 req… |
CVE-2026-55530 | Medium | 6.1 | 2026-08-25 | PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.58, ast_grep_rewrite lacks the @require_approval decorator used by sibling mutation tools… |
CVE-2026-55529 | Medium | 6.9 | 2026-08-25 | 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… |
CVE-2026-55528 | High | 8.2 | 2026-08-25 | PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.58, AgentServer exposes ServerConfig.auth_token but AgentServer._create_app does not chec… |
CVE-2026-55527 | High | 7.1 | 2026-08-25 | PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.58, the FileMemory constructor joins unsanitized user_id into self.user_path. A caller su… |
CVE-2026-55526 | High | 8.5 | 2026-08-25 | PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.58, spider_tools._host_is_blocked() does not resolve ordinary hostnames before scrape_pag… |
CVE-2026-55525 | High | 7.5 | 2026-08-25 | PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.58, the web_crawl function validates only the initial URL before _crawl_with_httpx uses h… |
CVE-2026-48169 | High | 8.8 | 2026-08-07 | PraisonAI is a multi-agent teams system. Versions prior to 0.1.4 of the PraisonAI Platform API have two authorization failures that together break workspace is… |
CVE-2026-55524 | High | 7.5 | 2026-08-05 | PraisonAI is a multi-agent teams system. In versions prior to 1.6.58, the web_crawl tool performs its SSRF check only on the initially supplied URL, allowing t… |
CVE-2026-55523 | | | 2026-08-05 | PraisonAI is a multi-agent teams system. In versions 1.5.128 through 1.6.57, the praisonaiagents.tools.web_crawl_tools.web_crawl() function is vulnerable to se… |
CVE-2026-55522 | High | 7.8 | 2026-08-05 | 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"… |
CVE-2026-48168 | Critical | 10.0 | 2026-08-05 | PraisonAI is a multi-agent teams system. In versions prior to 4.6.40, the bundled Claude GitHub Actions workflow is vulnerable to command injection because it… |
CVE-2026-47419 | High | 8.3 | 2026-07-21 | PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Versions prior to 0.1.4 have an* Insecure Direct Object Reference. The age… |
CVE-2026-47418 | High | 8.1 | 2026-07-21 | PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Versions prior to 0.1.4 have an Insecure Direct Object Reference. The proj… |
CVE-2026-47417 | High | 8.1 | 2026-07-21 | PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Versions prior to 0.1.4 have an Insecure Direct Object Reference. The comm… |
CVE-2026-47416 | Critical | 9.6 | 2026-07-21 | PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Versions prior to 0.1.4 are vulnerable to vertical privilege escalation. T… |
CVE-2026-47415 | High | 8.3 | 2026-07-21 | PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Versions prior to 0.1.4 have an Insecure Direct Object Reference. The issu… |
CVE-2026-47414 | High | 7.6 | 2026-07-21 | PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Versions prior to 0.1.4 have an Insecure Direct Object Reference. Five lab… |
CVE-2026-47413 | Critical | 9.6 | 2026-07-21 | PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Versions prior to 0.1.4 have aprivilege escalation / cross-tenant member i… |
CVE-2026-47412 | High | 8.1 | 2026-07-21 | PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Versions prior to 0.1.4 have an authorization bypass enabling destructive… |
CVE-2026-47411 | Medium | 6.5 | 2026-07-21 | PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Versions prior to 0.1.4 have an authorization bypass enabling workspace me… |
CVE-2026-47410 | Critical | 9.8 | 2026-07-21 | PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Versions prior to 0.1.4 have an insecure default cryptographic key. The JW… |
CVE-2026-47409 | High | 8.1 | 2026-07-21 | PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Versions prior to 0.1.4 have an authorization bypass enabling owner lockou… |
CVE-2026-47408 | Medium | 6.5 | 2026-07-21 | PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Versions prior to 0.1.4 have an Insecure Direct Object Reference. The `GET… |
CVE-2026-47407 | | | 2026-07-21 | PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Prior to version 0.1.4, the Platform server exposes resources under `/api/… |
CVE-2026-47406 | High | 8.1 | 2026-07-21 | PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Versions prior to 0.1.4 have an Insecure Direct Object Reference. The depe… |
CVE-2026-47405 | High | 8.8 | 2026-07-21 | PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Versions prior to 0.1.4 have a broken workspace authorization check that a… |
CVE-2026-47399 | High | 8.8 | 2026-07-21 | PraisonAI Platform is the platform layer for the PraisonAI multi-agent teams system. Prior to version 0.1.4, the workspace-scoped REST routes contain a systemi… |
CVE-2026-47398 | High | 8.1 | 2026-07-21 | 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_T… |
CVE-2026-47397 | | | 2026-07-21 | 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… |
CVE-2026-47396 | Critical | 9.8 | 2026-07-21 | PraisonAI is a multi-agent teams system. Prior to version 4.6.40, PraisonAI's call server exposes a network-facing agent control API without authentication whe… |
CVE-2026-47395 | Medium | 5.5 | 2026-07-21 | PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, PraisonAI's direct-prompt CL… |
CVE-2026-47394 | | | 2026-07-21 | PraisonAI is a multi-agent teams system. Prior to version 4.6.40, the fix for GHSA-9mqq-jqxf-grvw / CVE-2026-44336 is incomplete. The original advisory descrip… |
CVE-2026-47393 | Critical | 9.8 | 2026-07-21 | PraisonAI is a multi-agent teams system. CVE-2026-44338 (GHSA-6rmh-7xcm-cpxj) documents that PraisonAI ships a code-generator (`praisonai.deploy.api.generate_a… |
CVE-2026-47392 | Critical | 9.9 | 2026-07-21 | PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, `execute_code()` in `praison… |
CVE-2026-47391 | Critical | 9.8 | 2026-07-21 | PraisonAI is a multi-agent teams system. Prior to version 4.6.40, PraisonAI's first-party A2A server example exposes an unauthenticated A2A JSON-RPC endpoint a… |
CVE-2026-47390 | Medium | 5.5 | 2026-07-21 | PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, `spider_tools` URL validatio… |
CVE-2026-61446 | High | 8.4 | 2026-07-15 | PraisonAI (praisonaiagents) before 1.6.78 contains a remote code execution vulnerability in the plugin manager, which loads and executes arbitrary Python (.py)… |
CVE-2026-61443 | High | 8.1 | 2026-07-15 | PraisonAI before 1.6.78 contains a remote code execution vulnerability in SkillTools.run_skill_script() that executes scripts without path containment validati… |
CVE-2026-61440 | Medium | 6.5 | 2026-07-15 | PraisonAI Platform before 0.1.9 fails to properly authorize label and issue-label mutations, allowing workspace members to rename and recolor shared labels and… |
CVE-2026-61438 | High | 7.3 | 2026-07-15 | PraisonAI before 4.6.78 contains a remote code execution vulnerability in JobWorkflowExecutor._exec_inline_python() due to insufficient AST validation of workf… |
CVE-2026-61436 | High | 8.6 | 2026-07-15 | PraisonAI before 4.6.78 fails to verify Svix webhook signatures in AgentMail webhook mode, allowing unauthenticated attackers to forge message.received events… |
CVE-2026-61435 | High | 8.2 | 2026-07-15 | PraisonAI before 4.6.78 contains an authentication bypass in the Call API agent invocation endpoints (src/praisonai/praisonai/api/agent_invoke.py) when PRAISON… |
CVE-2026-61433 | High | 7.8 | 2026-07-15 | PraisonAI before 4.6.78 fails to safely encode deployment configuration values when generating Python source code for API servers. Attackers can inject arbitra… |
CVE-2026-61430 | High | 8.5 | 2026-07-15 | PraisonAI before 1.6.78 contains a server-side request forgery vulnerability in the web_crawl tool that validates hostnames at check time but re-resolves them… |
CVE-2026-61427 | High | 7.3 | 2026-07-15 | PraisonAI before 4.6.78 exposes the MCP HTTP-stream transport without authentication by default: the CLI --api-key option defaults to None, and the server only… |
CVE-2026-60087 | Medium | 6.1 | 2026-07-15 | PraisonAI before 1.6.78 caches tool approval decisions by tool name only, allowing attackers to reuse initial approvals for subsequent calls with arbitrary arg… |
CVE-2026-60085 | High | 7.5 | 2026-07-15 | PraisonAI before 4.6.78 contains an unenforced security policy vulnerability in the default Subprocess Sandbox backend where blocked_commands, blocked_paths, b… |
CVE-2026-61447 | Critical | 10.0 | 2026-07-11 | PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python() that executes LLM-generated Python code without AST valid… |
CVE-2026-61445 | Critical | 9.9 | 2026-07-11 | PraisonAI before 4.6.78 contains arbitrary file write and command execution vulnerabilities in the AICoder component due to missing path validation and command… |
CVE-2026-61442 | High | 7.1 | 2026-07-11 | PraisonAI Platform (praisonai-platform) before 0.1.9 fails to enforce owner/admin authorization on the PATCH routes for projects, issues, and agents, which onl… |
CVE-2026-61439 | High | 7.5 | 2026-07-11 | PraisonAI versions before 4.6.78 contain a prompt injection defense misconfiguration where the block threshold defaults to CRITICAL severity, allowing HIGH-lev… |
CVE-2026-61429 | High | 8.5 | 2026-07-11 | PraisonAI versions before 1.6.78 contain a server-side request forgery vulnerability in the Crawl4AI/Chromium backend that allows attackers to bypass SSRF vali… |
CVE-2026-61428 | High | 7.3 | 2026-07-11 | PraisonAI AgentMail versions before 4.6.78 lack signature verification in webhook mode, allowing unauthenticated attackers to inject messages with spoofed send… |
CVE-2026-61426 | High | 8.6 | 2026-07-11 | PraisonAI before 1.7.3 contains an insecure default configuration that binds to all interfaces with no API key requirement and wildcard CORS. Unauthenticated a… |
CVE-2026-60090 | Critical | 9.8 | 2026-07-11 | PraisonAI before 4.6.78 fails to validate the caller-controlled dimension argument in the PGVector and Cassandra knowledge-store create_collection() backends… |
CVE-2026-60088 | Medium | 5.5 | 2026-07-11 | PraisonAI before 4.6.78 fails to validate file path references in custom command templates, allowing attackers to read files outside the workspace. Attackers c… |
CVE-2026-61444 | Critical | 9.1 | 2026-07-10 | PraisonAI versions before 4.6.78 contain a code injection vulnerability in deploy/api.py where the agents_file parameter is directly interpolated into an f-str… |
CVE-2026-61441 | Medium | 6.5 | 2026-07-10 | PraisonAI Platform (praisonai-platform) before 0.1.9 improperly authorizes deletion of issue dependencies. The DELETE dependency route accepts either endpoint… |
CVE-2026-61437 | High | 7.8 | 2026-07-10 | PraisonAI (pip package praisonaiagents) before 1.6.78 contains an unsafe dynamic module loading vulnerability in AgentFlow._resolve_pydantic_class (src/praison… |
CVE-2026-61434 | High | 8.8 | 2026-07-10 | PraisonAI versions before 4.6.78 contain an allowlist bypass vulnerability in shell command execution that allows attackers to execute restricted commands via… |
CVE-2026-61432 | Medium | 5.7 | 2026-07-10 | PraisonAI (praisonaiagents) before 1.6.78 contains a path traversal vulnerability in the FastContext feature (praisonaiagents.context.fast). FastContextAgent.e… |