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.
CVE-2026-39891 is a high-severity code injection vulnerability in MervinPraison's PraisonAI versions prior to 4.5.115. The vulnerability arises because the create_agent_centric_tools() function returns tools that process file content using template rendering without properly escaping user input from agent.start(). This allows template expressions in the input to be executed as code rather than treated as literal text. The issue is fixed in version 4.5.115. No known exploits are reported in the wild, and the product is not a cloud service.
CVE-2026-39890 is a critical vulnerability in MervinPraison PraisonAI versions prior to 4.5.115. The vulnerability arises from unsafe deserialization of YAML files using the js-yaml library without disabling dangerous tags, allowing attackers to execute arbitrary JavaScript code remotely by uploading malicious agent definition files. This leads to remote code execution on the server hosting the vulnerable application. The issue is fixed in version 4.5.115. No known exploits in the wild have been reported yet.