CVE Database and Vulnerability Search
Search CVE and GHSA vulnerability records by identifier, title, vendor, product, package, or CWE. Filter by severity, CISA KEV, ransomware association, linked artifacts, and Nuclei templates; sort by publication date, CVSS, or EPSS.
| Vulnerability | Title and context | CVSS | EPSS | PoCs | Signals | STIX action |
|---|---|---|---|---|---|---|
CVE-2026-47398HIGH | PraisonAI: Arbitrary code execution via unguarded `spec.loader.exec_module` in `agents_generator.py` - sibling of CVE-2026-44334PraisonAI 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 remain completely unguarded in versions prior to 4.6.40. Both functions accept a module_path parameter sourced from YAML configuration and execute it without validation, signature chec… | CVSS8.1v3.1 | EPSS0.33% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-47397HIGH | PraisonAI has an Arbitrary File Write in Python APIPraisonAI 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. CWE-22Jul 21, 2026 | CVSS7.1v4.0 | EPSS0.381% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-47396CRITICAL | PraisonAI call server exposes unauthenticated agent listing, invocation, and deletion when CALL_SERVER_TOKEN is unsetPraisonAI 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 when `CALL_SERVER_TOKEN` is not configured. The affected component is the `praisonai.api.agent_invoke` router as mounted by `praisonai.api.call`. The authentication helper `verify_token()` fails open when `CALL_SERVER_TOKEN` is unset. Since every sensitive agent-control endpoint depends on this helper, starting the call server without a token… | CVSS9.8v3.1 | EPSS0.346% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-47395MEDIUM | PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model contextPraisonAI 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 CLI automatically expands `@url:` mentions in raw prompt text before agent execution begins. If a prompt contains `@url:<http-or-https-url>`, the CLI calls `MentionsParser.process(...)`. The `@url:` handler then performs a direct `urllib.request.urlopen()` request to the attacker-controlled URL and returns the response body. That response bo… CWE-200Jul 21, 2026 | CVSS5.5v3.1 | EPSS0.129% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-47394HIGH | PraisonAI vulnerable to unauthenticated arbitrary file read via MCP workflow.show, workflow.validate, deploy.validatePraisonAI 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 description named four vulnerable handlers in `mcp_server/adapters/cli_tools.py`. Commit `68cc9427` ("fix(security): harden MCP rules path handling…") added a `_resolve_rule_path()` helper and applied it to `rules.create`, `rules.show`, and `rules.delete`. `workflow.show` was left unchanged. Two adjacent handlers in the same file have the same pa… | CVSS8.7v4.0 | EPSS0.427% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-47393CRITICAL | PraisonAI `deploy --type api` emits a Flask server with authentication disabled by defaultPraisonAI is a multi-agent teams system. CVE-2026-44338 (GHSA-6rmh-7xcm-cpxj) documents that PraisonAI ships a code-generator (`praisonai.deploy.api.generate_api_server_code`) that emits a Flask API server with authentication disabled by default. Users who follow the documented quickstart (`praisonai deploy --type api`) get a server that binds to `0.0.0.0` per the recommended sample YAML, exposes `/chat` and `/agents` endpoints, runs `praisonai.run()` on user-supplied JSON input — LLM orchestrat… | CVSS9.8v3.1 | EPSS0.403% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-47392CRITICAL | PraisonAI vulnerable to sandbox escape via `print.__self__` builtins module leak in `execute_code` (subprocess mode)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 `praisonaiagents/tools/python_tools.py` (v1.6.37, subprocess sandbox mode) can be fully bypassed using `print.__self__` to retrieve the real Python `builtins` module, from which `__import__` can be extracted via `vars()` and runtime string construction. This achieves arbitrary OS command execution on the host, completely defeating the sandbox. Thi… | CVSS9.9v3.1 | EPSS0.602% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-47391CRITICAL | PraisonAI's unauthenticated A2A official example can reach real LLM-driven `eval()` tool executionPraisonAI 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 and registers a `calculate(expression)` tool implemented with Python `eval()`. The example also binds to `0.0.0.0`. A remote unauthenticated attacker can send `message/send` to `/a2a`; the request reaches `agent.chat()`, and a real LLM can invoke the registered `calculate` tool. In testing with `gemini/gemini-2.5-flash-lite`, this resulted … | CVSS9.8v3.1 | EPSS0.78% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-47390MEDIUM | PraisonAI spider_tools SSRF protection bypass via alternate loopback host encodingsPraisonAI 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 validation can be bypassed using alternate loopback host encodings. The tool contains a URL validation function intended to block local or unsafe targets before fetching attacker-controlled URLs. However, the validation only blocks a small set of exact host strings such as `localhost` and `127.0.0.1`. It does not normalize hostnames, resolve DNS, p… CWE-918Jul 21, 2026 | CVSS5.5v3.1 | EPSS0.165% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-44340HIGH | PraisonAI: Symlink-extraction bypass of `_safe_extractall` writes outside `dest_dir`PraisonAI is a multi-agent teams system. Prior to version 4.6.37, the _safe_extractall helper that all recipe pull, recipe publish, and recipe unpack flows route through validates each archive member's name for absolute paths, .. segments, and resolved-path escape — but does not validate member.linkname, does not reject symlink/hardlink members, and calls tar.extractall(dest_dir) without filter="data". A bundle that contains a symlink with a name inside dest_dir but a linkname pointing outside i… | CVSS8.7v4.0 | EPSS0.433% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-44339HIGH | PraisonAI has unsafe tool resolution in `ToolExecutionMixin.execute_tool`: undeclared `__main__` callables executePraisonAI is a multi-agent teams system. Prior to praisonai version 4.6.37 and praisonaiagents version 1.6.37, praisonaiagents resolves unresolved tool names against module globals and __main__ after it fails to match the declared tool list and the registry. With the default agent configuration, _perm_allow is None, so undeclared non-dangerous tool names are not rejected by the permission gate. An attacker who can influence tool-call names can therefore invoke unintended application callables th… CWE-470May 8, 2026 | CVSS8.6v3.1 | EPSS0.363% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-44338HIGH | PraisonAI ships and generates a legacy API server with authentication disabled by default, allowing unauthenticated workflow executionPraisonAI is a multi-agent teams system. From version 2.5.6 to before version 4.6.34, PraisonAI ships a legacy Flask API server with authentication disabled by default. When that server is used, any caller that can reach it can access /agents and trigger the configured agents.yaml workflow through /chat without providing a token. This issue has been patched in version 4.6.34. | CVSS7.3v3.1 | EPSS28.6% | PoCs2 | SignalsNot listed in CISA KEVNo known ransomware use1 Nuclei template | STIX |
CVE-2026-44337MEDIUM | PraisonAI knowledge-store backends interpolate unvalidated collection names into SQL and CQL queriesPraisonAI is a multi-agent teams system. From version 2.4.1 to before version 4.6.34, PraisonAI exposes optional SQL/CQL-backed knowledge-store implementations that build table and index identifiers from unvalidated name and collection arguments. Applications that pass untrusted collection names into these backends can trigger SQL or CQL injection. This issue has been patched in version 4.6.34. | CVSS6.3v3.1 | EPSS0.216% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-44336CRITICAL | PraisonAI MCP `tools/call` path-traversal and RCE via Python `.pth` injectionPraisonAI 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 para… | CVSS9.4v4.0 | EPSS0.62% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-40289CRITICAL | PraisonAI Browser Server allows unauthenticated WebSocket clients to hijack connected extension sessionsPraisonAI is a multi-agent teams system. In versions below 4.5.139 of PraisonAI and 1.5.140 of praisonaiagents, the browser bridge (praisonai browser start) is vulnerable to unauthenticated remote session hijacking due to missing authentication and a bypassable origin check on its /ws WebSocket endpoint. The server binds to 0.0.0.0 by default and only validates the Origin header when one is present, meaning any non-browser client that omits the header is accepted without restriction. An unauthen… CWE-306Apr 14, 2026 | CVSS9.1v3.1 | EPSS0.356% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-40288CRITICAL | PraisonAI: Critical RCE via `type: job` workflow YAMLPraisonAI is a multi-agent teams system. In versions below 4.5.139 of PraisonAI and 1.5.140 of praisonaiagents, the workflow engine is vulnerable to arbitrary command and code execution through untrusted YAML files. When praisonai workflow run <file.yaml> loads a YAML file with type: job, the JobWorkflowExecutor in job_workflow.py processes steps that support run: (shell commands via subprocess.run()), script: (inline Python via exec()), and python: (arbitrary Python script execution)—all withou… | CVSS9.8v3.1 | EPSS0.609% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-40287HIGH | PraisonAI has RCE via Automatic tools.py ImportPraisonAI is a multi-agent teams system. Versions 4.5.138 and below are vulnerable to arbitrary code execution through automatic, unsanitized import of a tools.py file from the current working directory. Components including call.py (import_tools_from_file()), tool_resolver.py (_load_local_tools()), and CLI tool-loading paths blindly import ./tools.py at startup without any validation, sandboxing, or user confirmation. An attacker who can place a malicious tools.py in the directory where Praison… | CVSS8.4v3.1 | EPSS0.246% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-40315HIGH | PraisonAI: SQLiteConversationStore didn't validate table_prefix when constructing SQL queriesPraisonAI is a multi-agent teams system. Prior to 4.5.133, there is an SQL identifier injection vulnerability in SQLiteConversationStore where the table_prefix configuration value is directly concatenated into SQL queries via f-strings without any validation or sanitization. Since SQL identifiers cannot be safely parameterized, an attacker who controls the table_prefix value (e.g., through from_yaml or from_dict configuration input) can inject arbitrary SQL fragments that alter query structure. … CWE-89Apr 14, 2026 | CVSS7.2v4.0 | EPSS0.297% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
PraisonAI: Hardcoded `approval_mode="auto"` in Chainlit UI Overrides Administrator Configuration, Enabling Unapproved Shell Command Execution## Summary The Chainlit UI modules (`chat.py` and `code.py`) hardcode `config.approval_mode = "auto"` after loading administrator configuration from the `PRAISON_APPROVAL_MODE` environment variable, silently overriding any "manual" or "scoped" approval setting. This defeats the human-in-the-loop approval gate for all ACP tool executions, including shell command execution via `subprocess.run(..., shell=True)`. An authenticated user can instruct the LLM agent to execute arbitrary single-command s… CWE-863Apr 10, 2026 | CVSS-v3.1 | EPSS- | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX | |
CVE-2026-40159MEDIUM | PraisonAI Exposes Sensitive Environment Variable via Untrusted MCP Subprocess ExecutionPraisonAI is a multi-agent teams system. Prior to 4.5.128, PraisonAI’s MCP (Model Context Protocol) integration allows spawning background servers via stdio using user-supplied command strings (e.g., MCP("npx -y @smithery/cli ...")). These commands are executed through Python’s subprocess module. By default, the implementation forwards the entire parent process environment to the spawned subprocess. As a result, any MCP command executed in this manner inherits all environment variables from the … | CVSS5.5v3.1 | EPSS0.182% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-40158HIGH | PraisonAI has Improper Control of Generation of Code ('Code Injection') and Protection Mechanism Failure in praisonaiPraisonAI is a multi-agent teams system. Prior to 4.5.128, PraisonAI's AST-based Python sandbox can be bypassed using type.__getattribute__ trampoline, allowing arbitrary code execution when running untrusted agent code. The _execute_code_direct function in praisonaiagents/tools/python_tools.py uses AST filtering to block dangerous Python attributes like __subclasses__, __globals__, and __bases__. However, the filter only checks ast.Attribute nodes, allowing a bypass. The sandbox relies on AST-b… | CVSS8.6v3.1 | EPSS0.24% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-40157CRITICAL | PraisonAI affected by arbitrary file write via path traversal in `praisonai recipe unpack`PraisonAI is a multi-agent teams system. Prior to 4.5.128, cmd_unpack in the recipe CLI extracts .praison tar archives using raw tar.extract() without validating archive member paths. A .praison bundle containing ../../ entries will write files outside the intended output directory. An attacker who distributes a malicious bundle can overwrite arbitrary files on the victim's filesystem when they run praisonai recipe unpack. This vulnerability is fixed in 4.5.128. CWE-22Apr 10, 2026 | CVSS9.4v4.0 | EPSS0.379% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-40154CRITICAL | PraisonAI Affected by Untrusted Remote Template Code ExecutionPraisonAI is a multi-agent teams system. Prior to 4.5.128, PraisonAI treats remotely fetched template files as trusted executable code without integrity verification, origin validation, or user confirmation, enabling supply chain attacks through malicious templates. This vulnerability is fixed in 4.5.128. CWE-829Apr 9, 2026 | CVSS9.3v3.1 | EPSS0.304% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-40151MEDIUM | PraisonAI Affected by Unauthenticated Information Disclosure of Agent Instructions via /api/agents in AgentOSPraisonAI is a multi-agent teams system. Prior to 4.5.128, the AgentOS deployment platform exposes a GET /api/agents endpoint that returns agent names, roles, and the first 100 characters of agent system instructions to any unauthenticated caller. The AgentOS FastAPI application has no authentication middleware, no API key validation, and defaults to CORS allow_origins=["*"] with host="0.0.0.0", making every deployment network-accessible and queryable from any origin by default. This vulnerabili… | CVSS5.3v3.1 | EPSS0.758% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware use1 Nuclei template | STIX |
CVE-2026-40149HIGH | PraisonAI has an Unauthenticated Allow-List Manipulation Bypasses Agent Tool Approval Safety ControlsPraisonAI is a multi-agent teams system. Prior to 4.5.128, the gateway's /api/approval/allow-list endpoint permits unauthenticated modification of the tool approval allowlist when no auth_token is configured (the default). By adding dangerous tool names (e.g., shell_exec, file_write) to the allowlist, an attacker can cause the ExecApprovalManager to auto-approve all future agent invocations of those tools, bypassing the human-in-the-loop safety mechanism that the approval system is specifically … | CVSS7.9v3.1 | EPSS0.227% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |