CVE-2026-47395 PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context

PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, PraisonAI's direct-prompt CLI automatically expands @url: mentions in raw prompt text before agent execution begins. If a prompt contains @url:, the CLI calls...

CVE-2026-47395 PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context

PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, PraisonAI's direct-prompt CLI automatically expands @url: mentions in raw prompt text before agent execution begins. If a prompt contains @url:, the CLI calls...

CVE-2026-47395 PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context

PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, PraisonAI's direct-prompt CLI automatically expands @url: mentions in raw prompt text before agent execution begins. If a prompt contains @url:, the CLI calls...

CVE-2026-47395

CVE-2026-47395 – PraisonAI CLI loopback/SSRF via @url: mentions Prior to PraisonAI v4.6.40 (and praisonaiagents v1.6.40), the direct-prompt CLI automatically expands @url:(http|https) prompts, performing an unrestricted urllib.request.urlopen() to the attacker-controlled URL. The fetched response...

EUVD-2026-46303

PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, PraisonAI's direct-prompt CLI automatically expands @url: mentions in raw prompt text before agent execution begins. If a prompt contains @url:, the CLI calls...

CVE-2026-47394 PraisonAI vulnerable to unauthenticated arbitrary file read via MCP workflow.show, workflow.validate, deploy.validate

PraisonAI is a multi-agent teams system. Prior to version 4.6.40, the fix for GHSA-9mqq-jqxf-grvw / CVE-2026-44336 is incomplete. The original advisory description named four vulnerable handlers in mcpserver/adapters/clitools.py. Commit 68cc9427 "fixsecurity: harden MCP rules path handling…" adde...

CVE-2026-47394 PraisonAI vulnerable to unauthenticated arbitrary file read via MCP workflow.show, workflow.validate, deploy.validate

PraisonAI is a multi-agent teams system. Prior to version 4.6.40, the fix for GHSA-9mqq-jqxf-grvw / CVE-2026-44336 is incomplete. The original advisory description named four vulnerable handlers in mcpserver/adapters/clitools.py. Commit 68cc9427 "fixsecurity: harden MCP rules path handling…" adde...

EUVD-2026-46302

PraisonAI is a multi-agent teams system. Prior to version 4.6.40, the fix for GHSA-9mqq-jqxf-grvw / CVE-2026-44336 is incomplete. The original advisory description named four vulnerable handlers in mcpserver/adapters/clitools.py. Commit 68cc9427 "fixsecurity: harden MCP rules path handling…" adde...

CVE-2026-47394

CVE-2026-47394 describes an unauthenticated file-read vulnerability in PraisonAI’s MCP server. The issue stems from a dispatcher in server.py that enforces no strict schema on JSON arguments fed to handlers (via kwargs ), allowing tools like workflow.show, workflow.validate, and deploy.validate t...

CVE-2026-47394 PraisonAI vulnerable to unauthenticated arbitrary file read via MCP workflow.show, workflow.validate, deploy.validate

PraisonAI is a multi-agent teams system. Prior to version 4.6.40, the fix for GHSA-9mqq-jqxf-grvw / CVE-2026-44336 is incomplete. The original advisory description named four vulnerable handlers in mcpserver/adapters/clitools.py. Commit 68cc9427 "fixsecurity: harden MCP rules path handling…" adde...

CVE-2026-47393 PraisonAI `deploy --type api` emits a Flask server with authentication disabled by default

PraisonAI is a multi-agent teams system. CVE-2026-44338 GHSA-6rmh-7xcm-cpxj documents that PraisonAI ships a code-generator praisonai.deploy.api.generateapiservercode that emits a Flask API server with authentication disabled by default. Users who follow the documented quickstart praisonai deploy...

CVE-2026-47393 PraisonAI `deploy --type api` emits a Flask server with authentication disabled by default

PraisonAI is a multi-agent teams system. CVE-2026-44338 GHSA-6rmh-7xcm-cpxj documents that PraisonAI ships a code-generator praisonai.deploy.api.generateapiservercode that emits a Flask API server with authentication disabled by default. Users who follow the documented quickstart praisonai deploy...

CVE-2026-47393 PraisonAI `deploy --type api` emits a Flask server with authentication disabled by default

PraisonAI is a multi-agent teams system. CVE-2026-44338 GHSA-6rmh-7xcm-cpxj documents that PraisonAI ships a code-generator praisonai.deploy.api.generateapiservercode that emits a Flask API server with authentication disabled by default. Users who follow the documented quickstart praisonai deploy...

CVE-2026-47393

PraisonAI's code generator for API servers (praisonai.deploy.api.generate_api_server_code) emits a Flask API server with authentication disabled by default. Default config sets auth_enabled=False and auth_token=None, causing check_auth() to short-circuit and accept unauthenticated requests to /ch...

CVE-2026-47392 PraisonAI vulnerable to sandbox escape via `print.__self__` builtins module leak in `execute_code` (subprocess mode)

PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, 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 modul...

EUVD-2026-46282

PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, 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 modul...

CVE-2026-47392

CVE-2026-47392 describes a sandbox escape in PraisonAI/praisonaiagents where evaluating code via execute_code() in subprocess sandbox mode can be bypassed by accessing the real builtins module through print.self , then retrieving import via vars() and constructing a dynamic attribute access to im...

CVE-2026-47392 PraisonAI vulnerable to sandbox escape via `print.__self__` builtins module leak in `execute_code` (subprocess mode)

PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, 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 modul...

CVE-2026-47392 PraisonAI vulnerable to sandbox escape via `print.__self__` builtins module leak in `execute_code` (subprocess mode)

PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, 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 modul...

CVE-2026-47390 PraisonAI spider_tools SSRF protection bypass via alternate loopback host encodings

PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, spidertools URL validation can be bypassed using alternate loopback host encodings. The tool contains a URL validation function intended to block local or unsafe...