CVE-2026-34935 PraisonAI: OS Command Injection in MCPHandler.parse_mcp_command()

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.openprocess with no validation, allowlist check, or sanitization at any hop, allowing arbitrary OS command...

CVE-2026-34935

Summary: PraisonAI’s MCP handling vulnerability (CVE-2026-34935) allowed arbitrary OS command execution because the --mcp input was split and passed through to subprocess without validation before version 4.5.69. The root cause was lack of input validation/allowlist at multiple hops, enabling com...

CVE-2026-34935 PraisonAI: OS Command Injection in MCPHandler.parse_mcp_command()

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.openprocess with no validation, allowlist check, or sanitization at any hop, allowing arbitrary OS command...

CVE-2026-34935

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.openprocess with no validation, allowlist check, or sanitization at any hop, allowing arbitrary OS command...

CVE-2026-34935 PraisonAI: OS Command Injection in MCPHandler.parse_mcp_command()

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.openprocess with no validation, allowlist check, or sanitization at any hop, allowing arbitrary OS command...

PraisonAI SQL注入漏洞

PraisonAI is a low-code multi-intelligent body collaboration framework. PraisonAI suffers from a SQL injection vulnerability that stems from the getalluserthreads function constructing raw SQL queries using unescaped thread IDs, which can be exploited by an attacker to cause SQL injection and gai...

CVE-2026-34937: Improper Neutralization of Special Elements used in an OS Command

PraisonAI is a multi-agent teams system. Prior to version 1.5.90, runpython in praisonai constructs a shell command string by interpolating user-controlled code into python3 -c " " and passing it to subprocess.run..., shell=True. The escaping logic only handles \ and ", leaving $ and backtick...

CVE-2026-34938: Protection Mechanism Failure

PraisonAI is a multi-agent teams system. Prior to version 1.5.90, executecode 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 safegetattr wrapper, achieving arbitrary ...

CVE-2026-34939: Inefficient Regular Expression Complexity

PraisonAI is a multi-agent teams system. Prior to version 4.5.90, MCPToolIndex.searchtools 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...

CVE-2026-34952: Missing Authentication for Critical Function

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 the...

CVE-2026-34934: Improper Neutralization of Special Elements used in an SQL Command

PraisonAI is a multi-agent teams system. Prior to version 4.5.90, the getalluserthreads function constructs raw SQL queries using f-strings with unescaped thread IDs fetched from the database. An attacker stores a malicious thread ID via updatethread. When the application loads the thread list, t...

CVE-2026-34953: Incorrect Authorization

PraisonAI is a multi-agent teams system. Prior to version 4.5.97, OAuthManager.validatetoken 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 t...

CVE-2026-34954: Server-Side Request Forgery (SSRF)

PraisonAI is a multi-agent teams system. Prior to version 1.5.95, FileTools.downloadfile in praisonaiagents validates the destination path but performs no validation on the url parameter, passing it directly to httpx.stream with followredirects=True. An attacker who controls the URL can reach any...

PraisonAI 安全漏洞

PraisonAI is a low-code multi-intelligence body collaboration framework by the individual developer Mervin Praison. PraisonAI suffers from a security vulnerability that stems from the OAuthManager.validatetoken function returning True for any token not found in its internal storage, which can be...

PraisonAI 安全漏洞

PraisonAI is a low-code multi-intelligent body collaboration framework. PraisonAI suffers from a security vulnerability that stems from the fact that the three-layer sandboxing of the executecode function can be completely bypassed, which can be exploited by an attacker to cause the execution of...

PraisonAI 安全漏洞

PraisonAI is a low-code multi-agent collaboration framework developed by Mervin Praison. Versions of PraisonAI prior to 1.5.90 contained security vulnerabilities. These vulnerabilities stemmed from the runpython function, which constructs commands by inserting user-controlled code into shell...

PraisonAI 安全漏洞

PraisonAI is a low-code multi-agent collaboration framework developed by Mervin Praison. Versions of PraisonAI prior to 4.5.90 contained security vulnerabilities. These vulnerabilities stemmed from the MCPToolIndex.searchtools function directly compiling the string provided by the caller into...

PraisonAI 操作系统命令注入漏洞

PraisonAI is a low-code multi-intelligent body collaboration framework. PraisonAI suffers from an operating system command injection vulnerability that stems from the --mcp CLI parameter being passed directly without any validation, whitelist checking, or cleanup, which can be exploited by an...

PraisonAI 安全漏洞

PraisonAI is a low-code multi-agent collaboration framework developed by Mervin Praison. Versions of PraisonAI prior to 4.5.90 contained security vulnerabilities. These vulnerabilities stemmed from the passthrough and apassthrough functions accepting an apibase parameter controlled by the caller...

CVE-2026-34936: Server-Side Request Forgery (SSRF)

PraisonAI is a multi-agent teams system. Prior to version 4.5.90, passthrough and apassthrough in praisonai accept a caller-controlled apibase parameter that is concatenated with endpoint and passed directly to httpx.Client.request when the litellm primary path raises AttributeError. No URL schem...