PraisonAI is a multi-agent teams system. In versions 4.5.139 and below, the GitHub Actions workflows are vulnerable to ArtiPACKED attack, a known credential leakage vector caused by using actions/checkout without setting persist-credentials: false. By default, actions/checkout writes the GITHUB_TOKEN (and sometimes ACTIONS_RUNTIME_TOKEN) into the .git/config file for persistence, and if any subsequent workflow step uploads artifacts (build outputs, logs, test results, etc.), these tokens can be inadvertently included. Since PraisonAI is a public repository, any user with read access can download these artifacts and extract the leaked tokens, potentially enabling an attacker to push malicious code, poison releases and PyPI/Docker packages, steal repository secrets, and execute a full supply chain compromise affecting all downstream users. The issue spans numerous workflow and action files across .github/workflows/ and .github/actions/. This issue has been fixed in version 4.5.140.

PraisonAI 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 unauthenticated network attacker can connect, send a start_session message, and the server will route it to the first idle browser-extension WebSocket (effectively hijacking that session) and then broadcast all resulting automation actions and outputs back to the attacker. This enables unauthorized remote control of connected browser automation sessions, leakage of sensitive page context and automation results, and misuse of model-backed browser actions in any environment where the bridge is network-reachable. This issue has been fixed in versions 4.5.139 of PraisonAI and 1.5.140 of praisonaiagents.

PraisonAI 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 without any validation, sandboxing, or user confirmation. The affected code paths include action_run() in workflow.py and _exec_shell(), _exec_inline_python(), and _exec_python_script() in job_workflow.py. An attacker who can supply or influence a workflow YAML file (particularly in CI pipelines, shared repositories, or multi-tenant deployment environments) can achieve full arbitrary command execution on the host system, compromising the machine and any accessible data or credentials. This issue has been fixed in versions 4.5.139 of PraisonAI and 1.5.140 of praisonaiagents.

PraisonAI 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 PraisonAI is launched (such as through a shared project, cloned repository, or writable workspace) achieves immediate arbitrary Python code execution in the host environment. This compromises the full PraisonAI process, the host system, and any connected data or credentials. This issue has been fixed in version 4.5.139.

PraisonAI 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. This enables unauthorized data access, such as reading internal SQLite tables like sqlite_master, and manipulation of query results through techniques like UNION-based injection. The vulnerability propagates from configuration input in config.py, through factory.py, to the SQL query construction in sqlite.py. Exploitation requires the ability to influence configuration input, and successful exploitation leads to internal schema disclosure and full query result tampering. This issue has been fixed in version 4.5.133.

PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, web_crawl's httpx fallback path passes user-supplied URLs directly to httpx.AsyncClient.get() with follow_redirects=True and no host validation. An LLM agent tricked into crawling an internal URL can reach cloud metadata endpoints (169.254.169.254), internal services, and localhost. The response content is returned to the agent and may appear in output visible to the attacker. This fallback is the default crawl path on a fresh PraisonAI installation (no Tavily key, no Crawl4AI installed). This vulnerability is fixed in 1.5.128.

PraisonAI 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 host process, including sensitive data such as API keys, authentication tokens, and database credentials. This behavior introduces a security risk when untrusted or third-party commands are used. In common scenarios where MCP tools are invoked via package runners such as npx -y, arbitrary code from external or potentially compromised packages may execute with access to these inherited environment variables. This creates a risk of unintended credential exposure and enables potential supply chain attacks through silent exfiltration of secrets. This vulnerability is fixed in 4.5.128.

PraisonAI 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-based filtering of attribute access but fails to account for dynamic attribute resolution via built-in methods such as type.getattribute, resulting in incomplete enforcement of security restrictions. The string '__subclasses__' is an ast.Constant, not an ast.Attribute, so it is never checked against the blocked list. This vulnerability is fixed in 4.5.128.

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.

PraisonAI is a multi-agent teams system. Prior to 4.5.128, PraisonAI automatically loads a file named tools.py from the current working directory to discover and register custom agent tools. This loading process uses importlib.util.spec_from_file_location and immediately executes module-level code via spec.loader.exec_module() without explicit user consent, validation, or sandboxing. The tools.py file is loaded implicitly, even when it is not referenced in configuration files or explicitly requested by the user. As a result, merely placing a file named tools.py in the working directory is sufficient to trigger code execution. This behavior violates the expected security boundary between user-controlled project files (e.g., YAML configurations) and executable code, as untrusted content in the working directory is treated as trusted and executed automatically. If an attacker can place a malicious tools.py file into a directory where a user or automated system (e.g., CI/CD pipeline) runs praisonai, arbitrary code execution occurs immediately upon startup, before any agent logic begins. This vulnerability is fixed in 4.5.128.

PraisonAI 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.

PraisonAI 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 vulnerability is fixed in 4.5.128.

PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, the execute_command function in shell_tools.py calls os.path.expandvars() on every command argument at line 64, manually re-implementing shell-level environment variable expansion despite using shell=False (line 88) for security. This allows exfiltration of secrets stored in environment variables (database credentials, API keys, cloud access keys). The approval system displays the unexpanded $VAR references to human reviewers, creating a deceptive approval where the displayed command differs from what actually executes. This vulnerability is fixed in 1.5.128.

PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, he list_files() tool in FileTools validates the directory parameter against workspace boundaries via _validate_path(), but passes the pattern parameter directly to Path.glob() without any validation. Since Python's Path.glob() supports .. path segments, an attacker can use relative path traversal in the glob pattern to enumerate arbitrary files outside the workspace, obtaining file metadata (existence, name, size, timestamps) for any path on the filesystem. This vulnerability is fixed in 1.5.128.

PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, the web_crawl() function in praisonaiagents/tools/web_crawl_tools.py accepts arbitrary URLs from AI agents with zero validation. No scheme allowlisting, hostname/IP blocklisting, or private network checks are applied before fetching. This allows an attacker (or prompt injection in crawled content) to force the agent to fetch cloud metadata endpoints, internal services, or local files via file:// URLs. This vulnerability is fixed in 1.5.128.

PraisonAI 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 designed to enforce. This vulnerability is fixed in 4.5.128.

PraisonAI is a multi-agent teams system. Prior to 4.5.128, the _safe_extractall() function in PraisonAI's recipe registry validates archive members against path traversal attacks but performs no checks on individual member sizes, cumulative extracted size, or member count before calling tar.extractall(). An attacker can publish a malicious recipe bundle containing highly compressible data (e.g., 10GB of zeros compressing to ~10MB) that exhausts the victim's disk when pulled via LocalRegistry.pull() or HttpRegistry.pull(). This vulnerability is fixed in 4.5.128.

PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, read_skill_file() in skill_tools.py allows reading arbitrary files from the filesystem by accepting an unrestricted skill_path parameter. Unlike file_tools.read_file which enforces workspace boundary confinement, and unlike run_skill_script which requires critical-level approval, read_skill_file has neither protection. An agent influenced by prompt injection can exfiltrate sensitive files without triggering any approval prompt. This vulnerability is fixed in 1.5.128.

PraisonAI is a multi-agent teams system. Prior to 4.5.128, the /media-stream WebSocket endpoint in PraisonAI's call module accepts connections from any client without authentication or Twilio signature validation. Each connection opens an authenticated session to OpenAI's Realtime API using the server's API key. There are no limits on concurrent connections, message rate, or message size, allowing an unauthenticated attacker to exhaust server resources and drain the victim's OpenAI API credits. This vulnerability is fixed in 4.5.128.

PraisonAI is a multi-agent teams system. Prior to 4.5.128, the WSGI-based recipe registry server (server.py) reads the entire HTTP request body into memory based on the client-supplied Content-Length header with no upper bound. Combined with authentication being disabled by default (no token configured), any local process can send arbitrarily large POST requests to exhaust server memory and cause a denial of service. The Starlette-based server (serve.py) has RequestSizeLimitMiddleware with a 10MB limit, but the WSGI server lacks any equivalent protection. This vulnerability is fixed in 4.5.128.

PraisonAI is a multi-agent teams system. Prior to 4.5.128, the /api/v1/runs endpoint accepts an arbitrary webhook_url in the request body with no URL validation. When a submitted job completes (success or failure), the server makes an HTTP POST request to this URL using httpx.AsyncClient. An unauthenticated attacker can use this to make the server send POST requests to arbitrary internal or external destinations, enabling SSRF against cloud metadata services, internal APIs, and other network-adjacent services. This vulnerability is fixed in 4.5.128.

PraisonAI is a multi-agent teams system. Prior to 4.5.128, deploy.py constructs a single comma-delimited string for the gcloud run deploy --set-env-vars argument by directly interpolating openai_model, openai_key, and openai_base without validating that these values do not contain commas. gcloud uses a comma as the key-value pair separator for --set-env-vars. A comma in any of the three values causes gcloud to parse the trailing text as additional KEY=VALUE definitions, injecting arbitrary environment variables into the deployed Cloud Run service. This vulnerability is fixed in 4.5.128.

PraisonAI is a multi-agent teams system. Prior to 4.5.128, the Flask API endpoint in src/praisonai/api.py renders agent output as HTML without effective sanitization. The _sanitize_html function relies on the nh3 library, which is not listed as a required or optional dependency in pyproject.toml. When nh3 is absent (the default installation), the sanitizer is a no-op that returns HTML unchanged. An attacker who can influence agent input (via RAG data poisoning, web scraping results, or prompt injection) can inject arbitrary JavaScript that executes in the browser of anyone viewing the API output. This vulnerability is fixed in 4.5.128.

PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, he memory hooks executor in praisonaiagents passes a user-controlled command string directly to subprocess.run() with shell=True at src/praisonai-agents/praisonaiagents/memory/hooks.py. No sanitization is performed and shell metacharacters are interpreted by /bin/sh before the intended command executes. Two independent attack surfaces exist. The first is via pre_run_command and post_run_command hook event types registered through the hooks configuration. The second and more severe surface is the .praisonai/hooks.json lifecycle configuration, where hooks registered for events such as BEFORE_TOOL and AFTER_TOOL fire automatically during agent operation. An agent that gains file-write access through prompt injection can overwrite .praisonai/hooks.json and have its payload execute silently at every subsequent lifecycle event without further user interaction. This vulnerability is fixed in 1.5.128.

PraisonAI is a multi-agent teams system. Prior to 4.5.121, the execute_command function and workflow shell execution are exposed to user-controlled input via agent workflows, YAML definitions, and LLM-generated tool calls, allowing attackers to inject arbitrary shell commands through shell metacharacters. This vulnerability is fixed in 4.5.121.

PraisonAI is a multi-agent teams system. Prior to 4.5.115, the create_agent_centric_tools() function returns tools (like acp_create_file) that process file content using template rendering. When user input from agent.start() is passed directly into these tools without escaping, template expressions in the input are executed rather than treated as literal text. This vulnerability is fixed in 4.5.115.

PraisonAI is a multi-agent teams system. Prior to 4.5.115, the AgentService.loadAgentFromFile method uses the js-yaml library to parse YAML files without disabling dangerous tags (such as !!js/function and !!js/undefined). This allows an attacker to craft a malicious YAML file that, when parsed, executes arbitrary JavaScript code. An attacker can exploit this vulnerability by uploading a malicious agent definition file via the API endpoint, leading to remote code execution (RCE) on the server. This vulnerability is fixed in 4.5.115.

PraisonAI is a multi-agent teams system. Prior to 4.5.115, the A2U (Agent-to-User) event stream server in PraisonAI exposes all agent activity without authentication. The create_a2u_routes() function registers the following endpoints with NO authentication checks: /a2u/info, /a2u/subscribe, /a2u/events/{stream_name}, /a2u/events/sub/{id}, and /a2u/health. This vulnerability is fixed in 4.5.115.

PraisonAI is a multi-agent teams system. Prior to 1.5.115, execute_code() in praisonaiagents.tools.python_tools defaults to sandbox_mode="sandbox", which runs user code in a subprocess wrapped with a restricted __builtins__ dict and an AST-based blocklist. The AST blocklist embedded inside the subprocess wrapper (blocked_attrs of python_tools.py) contains only 11 attribute names — a strict subset of the 30+ names blocked in the direct-execution path. The four attributes that form a frame-traversal chain out of the sandbox are all absent from the subprocess list (__traceback__, tb_frame, f_back, and f_builtins). Chaining these attributes through a caught exception exposes the real Python builtins dict of the subprocess wrapper frame, from which exec can be retrieved and called under a non-blocked variable name — bypassing every remaining security layer. This vulnerability is fixed in 1.5.115.

PraisonAI is a multi-agent teams system. Prior to 1.5.113, The PraisonAI templates installation feature is vulnerable to a "Zip Slip" Arbitrary File Write attack. When downloading and extracting template archives from external sources (e.g., GitHub), the application uses Python's zipfile.extractall() without verifying if the files within the archive resolve outside of the intended extraction directory. This vulnerability is fixed in 1.5.113.

PraisonAI is a multi-agent teams system. Prior to 1.5.113, PraisonAI's recipe registry publish endpoint writes uploaded recipe bundles to a filesystem path derived from the bundle's internal manifest.json before it verifies that the manifest name and version match the HTTP route. A malicious publisher can place ../ traversal sequences in the bundle manifest and cause the registry server to create files outside the configured registry root even though the request is ultimately rejected with HTTP 400. This is an arbitrary file write / path traversal issue on the registry host. It affects deployments that expose the recipe registry publish flow. If the registry is intentionally run without a token, any network client that can reach the service can trigger it. If a token is configured, any user with publish access can still exploit it. This vulnerability is fixed in 1.5.113.

PraisonAI is a multi-agent teams system. Prior to 1.5.113, PraisonAI's recipe registry pull flow extracts attacker-controlled .praison tar archives with tar.extractall() and does not validate archive member paths before extraction. A malicious publisher can upload a recipe bundle that contains ../ traversal entries and any user who later pulls that recipe will write files outside the output directory they selected. This is a path traversal / arbitrary file write vulnerability on the client side of the recipe registry workflow. It affects both the local registry pull path and the HTTP registry pull path. The checksum verification does not prevent exploitation because the malicious traversal payload is part of the signed bundle itself. This vulnerability is fixed in 1.5.113.

PraisonAI is a multi-agent teams system. Prior to 1.5.113, the Action Orchestrator feature contains a Path Traversal vulnerability that allows an attacker (or compromised agent) to write to arbitrary files outside of the configured workspace directory. By supplying relative path segments (../) in the target path, malicious actions can overwrite sensitive system files or drop executable payloads on the host. This vulnerability is fixed in 1.5.113.

PraisonAI is a multi-agent teams system. Prior to 1.5.113, _validate_path() calls os.path.normpath() first, which collapses .. sequences, then checks for '..' in normalized. Since .. is already collapsed, the check always passes. This makes the check completely useless and allows trivial path traversal to any file on the system. This vulnerability is fixed in 1.5.113.

PraisonAI is a multi-agent teams system. Prior to version 4.5.97, SubprocessSandbox in all modes (BASIC, STRICT, NETWORK_ISOLATED) calls subprocess.run() with shell=True and relies solely on string-pattern matching to block dangerous commands. The blocklist does not include sh or bash as standalone executables, allowing trivial sandbox escape in STRICT mode via sh -c '<command>'. This issue has been patched in version 4.5.97.

PraisonAI is a multi-agent teams system. Prior to version 1.5.95, FileTools.download_file() in praisonaiagents validates the destination path but performs no validation on the url parameter, passing it directly to httpx.stream() with follow_redirects=True. An attacker who controls the URL can reach any host accessible from the server including cloud metadata services and internal network services. This issue has been patched in version 1.5.95.

PraisonAI is a multi-agent teams system. Prior to version 4.5.97, OAuthManager.validate_token() returns True for any token not found in its internal store, which is empty by default. Any HTTP request to the MCP server with an arbitrary Bearer token is treated as authenticated, granting full access to all registered tools and agent capabilities. This issue has been patched in version 4.5.97.

PraisonAI is a multi-agent teams system. Prior to version 4.5.97, the PraisonAI Gateway server accepts WebSocket connections at /ws and serves agent topology at /info with no authentication. Any network client can connect, enumerate registered agents, and send arbitrary messages to agents and their tool sets. This issue has been patched in version 4.5.97.

PraisonAI is a multi-agent teams system. Prior to version 4.5.90, MCPToolIndex.search_tools() compiles a caller-supplied string directly as a Python regular expression with no validation, sanitization, or timeout. A crafted regex causes catastrophic backtracking in the re engine, blocking the Python thread for hundreds of seconds and causing a complete service outage. This issue has been patched in version 4.5.90.

PraisonAI is a multi-agent teams system. Prior to version 1.5.90, execute_code() in praisonai-agents runs attacker-controlled Python inside a three-layer sandbox that can be fully bypassed by passing a str subclass with an overridden startswith() method to the _safe_getattr wrapper, achieving arbitrary OS command execution on the host. This issue has been patched in version 1.5.90.

PraisonAI is a multi-agent teams system. Prior to version 1.5.90, run_python() in praisonai constructs a shell command string by interpolating user-controlled code into python3 -c "<code>" and passing it to subprocess.run(..., shell=True). The escaping logic only handles \ and ", leaving $() and backtick substitutions unescaped, allowing arbitrary OS command execution before Python is invoked. This issue has been patched in version 1.5.90.

PraisonAI is a multi-agent teams system. Prior to version 4.5.90, passthrough() and apassthrough() in praisonai accept a caller-controlled api_base parameter that is concatenated with endpoint and passed directly to httpx.Client.request() when the litellm primary path raises AttributeError. No URL scheme validation, private IP filtering, or domain allowlist is applied, allowing requests to any host reachable from the server. This issue has been patched in version 4.5.90.

PraisonAI is a multi-agent teams system. Prior to version 4.5.90, the get_all_user_threads function constructs raw SQL queries using f-strings with unescaped thread IDs fetched from the database. An attacker stores a malicious thread ID via update_thread. When the application loads the thread list, the injected payload executes and grants full database access. This issue has been patched in version 4.5.90.

PraisonAI is a multi-agent teams system. From version 4.5.15 to before version 4.5.69, the --mcp CLI argument is passed directly to shlex.split() and forwarded through the call chain to anyio.open_process() with no validation, allowlist check, or sanitization at any hop, allowing arbitrary OS command execution as the process user. This issue has been patched in version 4.5.69.