CVE-2026-34955

PraisonAI's SubprocessSandbox is vulnerable prior to version 4.5.97: it uses subprocess.run() with shell=True in all modes and blocks commands only by string-pattern matching, not recognizing sh/bash as standalone executables. This enables sandbox escape in STRICT mode via sh -c '' (and related b...

CVE-2026-34955 PraisonAI: Sandbox Escape via shell=True and Bypassable Blocklist in SubprocessSandbox

PraisonAI is a multi-agent teams system. Prior to version 4.5.97, SubprocessSandbox in all modes BASIC, STRICT, NETWORKISOLATED 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...

CVE-2026-34954

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...

CVE-2026-34954 PraisonAI: SSRF in FileTools.download_file() via Unvalidated URL

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...

CVE-2026-34954

PrašionAI (praisonaiagents) contains a SSRF vulnerability in FileTools.download_file(): it only validates the destination path and passes the unvalidated url directly to httpx.stream() with follow_redirects=True, allowing an attacker-controlled URL to reach any host accessible from the server, in...

CVE-2026-34953

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-2026-34953

PraisonAI (OAuthManager.validate_token) vulnerability: before v4.5.97, validate_token() returns True for any token not present in the empty internal store, causing any Bearer token on MCP HTTP requests to be treated as authenticated and granting full access to tools and agent capabilities. This i...

CVE-2026-34953 PraisonAI: Authentication Bypass in OAuthManager.validate_token()

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-2026-34953 PraisonAI: Authentication Bypass in OAuthManager.validate_token()

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...

EUVD-2026-18925

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-2026-34952 PraisonAI: Missing Authentication in WebSocket Gateway

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-2026-34952

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-2026-34939 PraisonAI: ReDoS via Unvalidated User-Controlled Regex in MCPToolIndex.search_tools()

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-2026-34939

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-2026-34939

PraisonAI is vulnerable to a Regular Expression Denial of Service (ReDoS) through MCPToolIndex.search_tools(), where the function compiles a caller-supplied string directly into a Python regex with no validation or timeout. A crafted pattern can trigger catastrophic backtracking, blocking the Pyt...

CVE-2026-34939 PraisonAI: ReDoS via Unvalidated User-Controlled Regex in MCPToolIndex.search_tools()

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-2026-34939 PraisonAI: ReDoS via Unvalidated User-Controlled Regex in MCPToolIndex.search_tools()

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-2026-34938 PraisonAI: Python Sandbox Escape via str Subclass startswith() Override in execute_code

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-2026-34938

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-2026-34938

PraisonAI contains a Python sandbox escape in the execute_code() function of praisonai-agents. Prior to version 1.5.90, the three-layer sandbox can be bypassed by passing a str subclass with an overridden startswith() to the _safe_getattr wrapper, enabling arbitrary OS command execution on the ho...