MervinPraison PraisonAI

• CVE-2026-57117 High 8.8 PraisonAI: Compute-bridged file tools allow shell command injection 0.6%
• CVE-2026-57146 High 7.5 PraisonAI A2U incomplete authentication fix leaves current serve command unauthenticated by default 0.5%
• CVE-2026-57144 High 8.8 PraisonAI SandlockSandbox falls back to unrestricted subprocess execution when Landlock is unavailable 0.2%
• CVE-2026-57142 High 7.8 PraisonAI recipe workflow policy can be bypassed by declaring and YAML-approving dangerous tools outside TEMPLATE.yaml 0.2%
• CVE-2026-57121 High 8.1 PraisonAI: Missing ownership check on DELETE endpoints allows members to delete others' content in Platform API 0.3%
• CVE-2026-57116 Critical 9.8 PraisonAI: AgentOS remains unauthenticated after GHSA-pm96 patched version and allows remote agent invocation 0.4%
• CVE-2026-57114 High 7.2 PraisonAI: Jobs webhook SSRF protection bypass via DNS rebinding 0.3%
• CVE-2026-57113 High 8.1 PraisonAI GitHub template cache path traversal allows outside-cache file write and directory deletion 0.4%
• CVE-2026-56840 High 8.8 PraisonAI: HTTPApproval dashboard renders tool arguments as raw HTML, allowing approval-page XSS to approve dangerous tools 0.4%
• CVE-2026-56838 High 7.8 PraisonAI recipe.run_stream skips dangerous-tool policy enforcement 0.1%
• CVE-2026-56837 High 8.6 PraisonAI LinearBot processes unsigned webhooks when LINEAR_WEBHOOK_SECRET is missing 0.2%
• CVE-2026-56836 High 8.2 PraisonAI recipe serve Typer command bypasses the non-localhost authentication guard 0.3%
• CVE-2026-56835 High 8.3 PraisonAI Slack app_mention bypasses configured user/channel authorization 0.2%
• CVE-2026-56834 High 7.5 PraisonAI dynamic-context artifact tools read arbitrary host files outside artifact storage 0.4%
• CVE-2026-56833 High 7.5 PraisonAI Dynamic Context history and terminal tools read files outside configured storage via path traversal 0.5%
• CVE-2026-56832 High 8.8 PraisonAI DiscordApproval accepts unrelated channel messages as dangerous-tool approvals 0.1%
• CVE-2026-57118 Critical 9.8 PraisonAI AgentTeam.launch exposes unauthenticated remote agent listing and invocation endpoints 0.4%
• CVE-2026-62176 Critical 9.1 PraisonAI: Code Injection via f-string Interpolation in Deploy API Server Generation 0.5%
• CVE-2026-57147 Critical 9.8 praisonai-platform: default JWT signing secret 'dev-secret-change-me' enables token forgery 0.8%
• CVE-2026-57148 Critical 9.8 praisonai-platform 0.1.4 still boots on the hardcoded JWT secret dev-secret-change-me (default-open production guard) 0.6%
• CVE-2026-57140 Critical 9.4 PraisonAI AgentOS exposes unauthenticated agent listing and invocation 0.6%
• CVE-2026-57139 Critical 9.8 PraisonAI MCPServer exposes unauthenticated HTTP tools/call 0.8%
• CVE-2026-57133 High 8.8 PraisonAI utility shell safe-command wrapper allowlist bypass via shell chaining 0.8%
• CVE-2026-57135 High 7.6 PraisonAI SandboxExecutor network-isolated mode does not block non-proxy-aware network clients 0.4%
• CVE-2026-57134 High 8.2 PraisonAI MCPSecurity Basic/OAuth authentication policies accept invalid credentials without validation 0.4%
• CVE-2026-57138 Critical 9.9 PraisonAI codeMode sandbox escape via Function constructor 0.7%
• CVE-2026-57136 High 8.8 PraisonAI SandboxExecutor allowedCommands bypass via shell chaining 0.5%
• CVE-2026-57137 High 8.8 PraisonAI AgentLoop onToolCall approval runs after tool execution 0.5%
• CVE-2026-57141 Critical 9.8 PraisonAI: Remote Code Execution via Sandbox Escape in `codeMode` Tool 0.7%
• CVE-2026-57112 High 8.3 PraisonAI ToolsMCPServer legacy SSE transport accepts attacker Host/Origin and exposes registered tools 0.2%
• CVE-2026-57145 Critical 9.1 PraisonAI: Arbitrary File Read/Write via `multiedit` Tool Without Path Validation 0.5%
• CVE-2026-57132 High 8.2 PraisonAI: PRAISONAI_CALL_AUTH=disabled environment variable unconditionally disables authentication 0.5%
• CVE-2026-57131 Critical 9.8 praisonai: Jobs API exposes agent-execution endpoints with no authentication 1.0%
• CVE-2026-57124 Critical 9.8 PraisonAI UI MCP connect endpoint allows unauthenticated local command execution 1.0%
• CVE-2026-57122 High 8.6 PraisonAI: Webhook signature verification skipped (fail-open) when secret unset, allowing forged inbound webhooks (WhatsApp & Linear bots) 0.2%
• CVE-2026-57127 Critical 9.8 praisonai: recipe serve auth middleware silently disables itself when no secret is set 0.9%
• CVE-2026-56839 High 7.3 PraisonAI Code agent tools fail open without a workspace boundary 0.4%
• CVE-2026-57119 High 7.5 PraisonAI: Unauthenticated Local File Inclusion via agent_file path in the Jobs API 0.5%
• CVE-2026-57126 High 8.5 praisonaiagents: SSRF guard validates literal IPs only and never resolves DNS 0.4%
• CVE-2026-57128 Medium 4.3 PraisonAI: Unauthenticated Event Injection via SSE `/publish` Endpoint 0.3%
• CVE-2026-57115 Medium 6.5 PraisonAI: SpiderTools redirect-target SSRF protection bypass 0.4%
• CVE-2026-57125 Critical 9.8 PraisonAI: Unauthenticated RCE via Jobs API + Approval Bypass 0.6%
• CVE-2026-55536 Critical 9.1 Browser Server WebSocket origin validation bypass via unanchored regex (patch bypass of CVE-2026-40289 / GHSA-8x8f-54wf-vv92) 0.5%
• CVE-2026-55532 High 7.6 PraisonAI: Origin-validation bypass (startswith prefix match) enables unauthenticated cross-site request forgery against the PraisonAI MCP HTTP server 0.2%
• CVE-2026-55533 High 8.2 PraisonAI: Authentication fail-open in Recipe server allows unauthenticated access when API key or JWT auth is configured without a secret 0.5%
• CVE-2026-55539 High 8.6 PraisonAI: [Auth Bypass] PraisonAI async Jobs API (`/api/v1/runs`) has no authentication — unauthenticated job execution, result theft, cancel and delete 0.6%
• CVE-2026-55527 High 7.1 PraisonAI: Arbitrary file write via unsanitized `user_id` in `FileMemory.__init__()` — path traversal to any writable location 0.5%
• CVE-2026-55541 High 8.8 PraisonAI: `--api-key` flag on `praisonai serve` is not properly enforced 0.5%
• CVE-2026-55535 Medium 6.8 PraisonAI: Server-Side Request Forgery via DNS rebinding bypass in webhook_url validation 0.3%
• CVE-2026-55537 High 7.1 PraisonAI: Webhook SSRF via DNS fail-open in `JobSubmitRequest.validate_webhook_url()` — bypass of CVE-2026-40114 0.3%