PT-2026-61791

Summary The published npm package praisonai exports createAgentLoop, whose onToolCall callback is documented and exampled as an approval hook. The implementation calls PraisonAI's generateText wrapper with the caller's executable tools first, receives toolResults, and only then calls onToolCall...

CVE-2026-56076: Permissive Cross-domain Policy with Untrusted Domains

PraisonAI before 1.5.128 contains a cross-origin agent execution vulnerability in the AGUI endpoint that allows remote attackers to trigger arbitrary agent execution. The POST /agui endpoint lacks authentication and hardcodes Access-Control-Allow-Origin: headers, combined with Starlette's...

PT-2026-61781

Name of the Vulnerable Software and Affected Versions praisonai version 4.6.48 Description The recipe serve authentication middleware fails open when no secret is configured. Specifically, the APIKeyAuthMiddleware and JWTAuthMiddleware in praisonai/recipe/serve.py contain logic that allows reques...

CVE-2026-56074: Incorrect Authorization

PraisonAI before 1.5.128 caches tool approval decisions by tool name only, not by invocation arguments, allowing subsequent executecommand calls to bypass approval prompts. Attackers can exploit this by obtaining initial approval for a benign command, then silently exfiltrate API keys and...

PT-2026-61786

Name of the Vulnerable Software and Affected Versions PraisonAI affected versions not specified Description Setting the PRAISONAI CALL AUTH variable to disabled completely bypasses all authentication for the /api/v1/agents/id/invoke endpoint. This occurs because the verify token function returns...

PT-2026-61784

Name of the Vulnerable Software and Affected Versions praisonai-agents affected versions not specified Description The email search tool in src/praisonai-agents/praisonaiagents/tools/email tools.py is susceptible to IMAP injection. The issue occurs because the tool constructs IMAP SEARCH commands...

PT-2026-61778

PraisonAI is a multi-agent teams system. Prior to 4.6.59, the default UI host applications expose POST /api/mcp/connect without mandatory authentication and accept caller-controlled command and args values that PraisonAIUI passes to StdioMCPClient to start a local process. Because the UI commands...

PT-2026-61780

Name of the Vulnerable Software and Affected Versions praisonaiagents versions 1.6.39 and earlier PraisonAI versions 4.6.39 and earlier Description A Server-Side Request Forgery SSRF issue exists because the SSRF guard only validates literal IP address encodings and does not perform DNS resolutio...

PT-2026-53133

praisonai-platform: default JWT signing secret dev-secret-change-me Researcher: Kai Aizen — SnailSploit @SnailSploit, Adversarial & Offensive Security Research Target: https://github.com/MervinPraison/PraisonAI --- Package: praisonai-platform on PyPI Latest version and version tested: 0.1.4,...

PT-2026-61766

Name of the Vulnerable Software and Affected Versions praisonaiagents versions 0.6.0 through 1.6.58 praisonai versions 3.10.0 through 4.6.58 Description The run sse function in ToolsMCPServer creates a Starlette MCP HTTP+SSE server that fails to validate the Origin and Host headers and does not...

PT-2026-61793

Name of the Vulnerable Software and Affected Versions PraisonAI versions 1.5.0 through 1.7.1 Description In the multi-agent teams system, the MCPServer.startHttp function in src/praisonai-ts/src/mcp/server.ts binds without host restrictions and forwards all HTTP POST requests to the handleRequest...

The vulnerability of the PraisonAI framework, related to the lack of authentication for critical functions, allows attackers to gain unauthorized access to protected information.

The vulnerability of the PraisonAI framework is related to the lack of authentication for critical functions. Exploiting this vulnerability could allow an attacker, operating remotely, to gain unauthorized access to protected information...

CVE-2026-44337

PraisonAI is a multi-agent teams system. From version 2.4.1 to before version 4.6.34, PraisonAI exposes optional SQL/CQL-backed knowledge-store implementations that build table and index identifiers from unvalidated name and collection arguments. Applications that pass untrusted collection names...

CVE-2026-41497

PraisonAI is a multi-agent teams system. Prior to version 4.6.9, 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 t...

CVE-2026-40287

PraisonAI is a multi-agent teams system. Versions 4.5.138 and below are vulnerable to arbitrary code execution through automatic, unsanitized import of a tools.py file from the current working directory. Components including call.py importtoolsfromfile, toolresolver.py loadlocaltools, and CLI...

CVE-2026-40113

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 openaimodel, openaikey, and openaibase without validating that these values do not contain commas. gcloud use...

CVE-2026-40313

PraisonAI is a multi-agent teams system. In versions 4.5.139 and below, the GitHub Actions workflows are vulnerable to ArtiPACKED attack, a known credential leakage vector caused by using actions/checkout without setting persist-credentials: false. By default, actions/checkout writes the...

CVE-2026-40289

PraisonAI is a multi-agent teams system. In versions below 4.5.139 of PraisonAI and 1.5.140 of praisonaiagents, the browser bridge praisonai browser start is vulnerable to unauthenticated remote session hijacking due to missing authentication and a bypassable origin check on its /ws WebSocket...

CVE-2026-40088

PraisonAI is a multi-agent teams system. Prior to 4.5.121, the executecommand 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...

CVE-2026-40158

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 executecodedirect function in praisonaiagents/tools/pythontools.py uses AST...