EUVD-2026-42895

PraisonAI pip package praisonaiagents before 1.6.78 automatically loads defaults from a project-local .praisonai/config.toml when constructing an Agent, and does not validate the defaults.output.outputfile path. A repository-controlled config file can set outputfile to an absolute or '..' travers...

CVE-2026-60086 PraisonAI before 4.6.78 Prompt Injection Defense Bypass

PraisonAI before 4.6.78 contains a prompt injection defense bypass vulnerability where the injection defense only blocks threats classified as CRITICAL, requiring three or more detector families to match simultaneously. Attackers can craft single or double-vector prompt injections that are...

CVE-2026-60086

PraisonAI before 4.6.78 contains a prompt injection defense bypass vulnerability where the injection defense only blocks threats classified as CRITICAL, requiring three or more detector families to match simultaneously. Attackers can craft single or double-vector prompt injections that are...

CVE-2026-60089 PraisonAI before 1.6.78 Path Traversal via config.toml

PraisonAI pip package praisonaiagents before 1.6.78 automatically loads defaults from a project-local .praisonai/config.toml when constructing an Agent, and does not validate the defaults.output.outputfile path. A repository-controlled config file can set outputfile to an absolute or '..' travers...

PT-2026-57194

Name of the Vulnerable Software and Affected Versions praisonaiagents versions prior to 1.6.78 Description An unsafe dynamic module loading issue exists in the AgentFlow. resolve pydantic class function. When a workflow step utilizes a string output pydantic reference, the framework imports a...

PT-2026-57196

Name of the Vulnerable Software and Affected Versions PraisonAI versions prior to 4.6.78 Description A code injection issue exists in the deploy/api.py file. The agents file parameter is directly interpolated into an f-string without proper sanitization. This interpolated string is used to genera...

CVE-2026-58653

PraisonAI before 0.1.7 fails to validate that projectid in issue create and update request bodies belongs to the URL workspace. An attacker can create issues referencing projects from other workspaces, causing cross-tenant data pollution in project statistics aggregation without workspace...

CVE-2026-58653

CVE-2026-58653 affects PraisonAI prior to 0.1.7, where issue creation/update does not validate that project_id matches the URL workspace. This allows an attacker to reference projects from other workspaces, causing cross-tenant data pollution in project statistics aggregation without workspace co...

CVE-2026-58653 PraisonAI - Authorization Bypass via Unvalidated project_id in Issue Create/Update

PraisonAI before 0.1.7 fails to validate that projectid in issue create and update request bodies belongs to the URL workspace. An attacker can create issues referencing projects from other workspaces, causing cross-tenant data pollution in project statistics aggregation without workspace...

CVE-2026-58653 PraisonAI - Authorization Bypass via Unvalidated project_id in Issue Create/Update

PraisonAI before 0.1.7 fails to validate that projectid in issue create and update request bodies belongs to the URL workspace. An attacker can create issues referencing projects from other workspaces, causing cross-tenant data pollution in project statistics aggregation without workspace...

PYSEC-2026-463 PraisonAI vulnerable to sandbox escape via `print.__self__` builtins module leak in `execute_code` (subprocess mode)

Summary executecode in praisonaiagents/tools/pythontools.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 executio...

PYSEC-2026-483 PraisonAI vulnerable to sandbox escape via `print.__self__` builtins module leak in `execute_code` (subprocess mode)

Summary executecode in praisonaiagents/tools/pythontools.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 executio...

PraisonAI vulnerable to sandbox escape via `print.__self__` builtins module leak in `execute_code` (subprocess mode)

Summaryexecutecode in praisonaiagents/tools/pythontools.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...

PYSEC-2026-466 PraisonAI call server exposes unauthenticated agent listing, invocation, and deletion when CALL_SERVER_TOKEN is unset

Summary PraisonAI's call server exposes a network-facing agent control API without authentication when CALLSERVERTOKEN is not configured. The affected component is the praisonai.api.agentinvoke router as mounted by praisonai.api.call. The authentication helper verifytoken fails open when...

PYSEC-2026-484 PraisonAI: Python Sandbox Escape via str Subclass startswith() Override in execute_code

Summary 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 OS command execution on the host. Details pythontools.py:2...

PYSEC-2026-476 PraisonAI Vulnerable Untrusted Remote Template Code Execution

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. --- Description When a user installs a template from a remote source e.g., GitHub,...

PYSEC-2026-478 PraisonAI's unauthenticated A2A official example can reach real LLM-driven `eval()` tool execution

Summary The first-party PraisonAI A2A server example combines three behaviors into a remotely exploitable Critical chain: 1. The example exposes an A2A server without configuring authtoken. 2. The same example binds the server to 0.0.0.0. 3. The example registers a calculateexpression tool...

PYSEC-2026-468 PraisonAI Has Authentication Bypass via OAuthManager.validate_token()

Summary 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 to all registered tools and agent capabilities. Details...

PYSEC-2026-474 PraisonAI Has Missing Authentication in WebSocket Gateway

Summary 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. Details gateway/server.py:242 source -...

PYSEC-2026-473 PraisonAI has an incomplete fix for CVE-2026-34935 - OS Command Injection

Summary The fix for PraisonAI's MCP command handling does not add a command allowlist or argument validation to parsemcpcommand, allowing arbitrary executables like bash, python, or /bin/sh with inline code execution flags to pass through to subprocess execution. Affected Package - Ecosystem: PyP...