MervinPraison PraisonAI

• CVE-2026-55538 High 7.3 PraisonAI: [Auth Bypass] `praisonai serve agents --api-key` is silently ignored — agent-invocation routes (`POST /agents`, `POST /agents/{agent_name}`) run unauthenticated 0.4%
• CVE-2026-55540 High 7.1 PraisonAI: [Path Traversal] agent tools escape the configured workspace via symlinks 0.4%
• CVE-2026-55530 Medium 6.1 PraisonAI: ast_grep_rewrite rewrites arbitrary files without the @require_approval gate enforced on every sibling mutation tool 0.2%
• CVE-2026-55534 High 8.6 PraisonAI serve agents --api-key is ignored, allowing unauthenticated remote agent execution 0.5%
• CVE-2026-55526 High 8.5 PraisonAI: SSRF protection bypass in `spider_tools._host_is_blocked()` via DNS-resolved hostnames (`127.0.0.1.nip.io`) 0.4%
• CVE-2026-55531 Medium 6.5 PraisonAI: Unauthenticated unbounded session accumulation in the PraisonAI MCP HTTP server (memory exhaustion; session TTL never enforced) 0.5%
• CVE-2026-55528 High 8.2 praisonaiagents: AgentServer declares auth_token but never enforces it on any route (CWE-862) 0.5%
• CVE-2026-55529 Medium 6.9 PraisonAI: Origin validation bypass in MCP HTTP Stream transport allows browser-mediated unauthenticated tool execution on local MCP server 0.2%
• CVE-2026-55525 High 7.5 PraisonAI: SSRF via redirect-following in praisonaiagents web_crawl 0.5%
• CVE-2026-55524 High 7.5 PraisonAI: SSRF in web_crawl tool via redirect-following and DNS rebinding (validate-then-fetch gap) 0.2%
• CVE-2026-55523 High 7.7 PraisonAI has a`web_crawl` SSRF protection bypass via unchecked redirect targets 0.5%
• CVE-2026-55522 High 7.8 PraisonAI workflow include bypasses tools.py autoload opt-in and executes included recipe code 0.2%
• CVE-2026-48168 Critical 10.0 PraisonAI: GitHub Actions Claude workflow command injection via unquoted PR branch name 1.5%
• CVE-2026-47398 High 8.1 PraisonAI: Arbitrary code execution via unguarded `spec.loader.exec_module` in `agents_generator.py` - sibling of CVE-2026-44334 0.5%
• CVE-2026-47397 High 7.1 PraisonAI has an Arbitrary File Write in Python API 0.5%
• CVE-2026-47396 Critical 9.8 PraisonAI call server exposes unauthenticated agent listing, invocation, and deletion when CALL_SERVER_TOKEN is unset 0.4%
• CVE-2026-47395 Medium 5.5 PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context 0.2%
• CVE-2026-47394 High 8.7 PraisonAI vulnerable to unauthenticated arbitrary file read via MCP workflow.show, workflow.validate, deploy.validate 0.5%
• CVE-2026-47393 Critical 9.8 PraisonAI `deploy --type api` emits a Flask server with authentication disabled by default 0.6%
• CVE-2026-47392 Critical 9.9 PraisonAI vulnerable to sandbox escape via `print.__self__` builtins module leak in `execute_code` (subprocess mode) 0.9%
• CVE-2026-47391 Critical 9.8 PraisonAI's unauthenticated A2A official example can reach real LLM-driven `eval()` tool execution 1.5%
• CVE-2026-47390 Medium 5.5 PraisonAI spider_tools SSRF protection bypass via alternate loopback host encodings 0.2%
• CVE-2026-61446 High 8.4 PraisonAI before 1.6.78 Remote Code Execution via Plugin Auto-Discovery 0.3%
• CVE-2026-61443 High 8.1 PraisonAI before 1.6.78 Remote Code Execution via SkillTools 0.6%
• CVE-2026-61440 Medium 6.5 PraisonAI Platform before 0.1.9 Authorization Bypass via Label Endpoints 0.3%
• CVE-2026-61438 High 7.3 PraisonAI before 4.6.78 Remote Code Execution via Broken AST Sandbox 0.3%
• CVE-2026-61436 High 8.6 PraisonAI before 4.6.78 Missing Webhook Signature Verification 0.4%
• CVE-2026-61435 High 8.2 PraisonAI before 4.6.78 Authentication Bypass via Host Header Spoofing 0.5%
• CVE-2026-61433 High 7.8 PraisonAI before 4.6.78 Code Injection via API deployment generator 0.2%
• CVE-2026-61430 High 8.5 PraisonAI before 1.6.78 DNS Rebinding SSRF via web_crawl 0.3%
• CVE-2026-61427 High 7.3 PraisonAI before 4.6.78 Authentication Bypass via HTTP-stream 0.4%
• CVE-2026-60087 Medium 6.1 PraisonAI before 1.6.78 Tool Approval Cache Bypass 0.3%
• CVE-2026-60085 High 7.5 PraisonAI before 4.6.78 Unenforced Security Policy in Subprocess Sandbox 0.3%
• CVE-2026-61447 Critical 10.0 PraisonAI before 1.6.78 Remote Code Execution via CodeAgent 15.2%
• CVE-2026-61445 Critical 9.9 PraisonAI before 4.6.78 Arbitrary File Write and Command Execution 0.6%
• CVE-2026-61442 High 7.1 PraisonAI Platform before 0.1.9 Authorization Bypass via PATCH 0.3%
• CVE-2026-61439 High 7.5 PraisonAI before 4.6.78 Prompt Injection Defense Bypass 0.3%
• CVE-2026-61429 High 8.5 PraisonAI before 1.6.78 SSRF via Crawl4AI Chromium backend 0.3%
• CVE-2026-61428 High 7.3 PraisonAI AgentMail before 4.6.78 Message Injection via Webhook 0.3%
• CVE-2026-61426 High 8.6 PraisonAI before 1.7.3 Unauthenticated Agent Access via Insecure Defaults 0.4%
• CVE-2026-60090 Critical 9.8 PraisonAI before 4.6.78 SQL/CQL Injection via vector dimension 0.7%
• CVE-2026-60088 Medium 5.5 PraisonAI before 4.6.78 Path Traversal via Custom Commands 0.2%
• CVE-2026-61444 Critical 9.1 PraisonAI before 4.6.78 Code Injection via f-string 0.5%
• CVE-2026-61441 Medium 6.5 PraisonAI Platform before 0.1.9 Authorization Bypass via Dependencies 0.3%
• CVE-2026-61437 High 7.8 PraisonAI before 1.6.78 Remote Code Execution via tools.py 0.2%
• CVE-2026-61434 High 8.8 PraisonAI before 4.6.78 Allowlist Bypass via find -exec 0.7%
• CVE-2026-61432 Medium 5.7 PraisonAI FastContext before 1.6.78 Path Traversal 0.3%
• CVE-2026-61431 Medium 5.5 PraisonAI before 4.6.78 Path Traversal via ContextGatherer 0.4%
• CVE-2026-60091 High 7.2 PraisonAI before 4.6.78 Unauthenticated SSRF via webhook_url 0.2%
• CVE-2026-60089 Medium 5.5 PraisonAI before 1.6.78 Path Traversal via config.toml 0.2%