Mervinpraison Praisonai

75 CVEs affecting Mervinpraison Praisonai. Latest disclosed: 2026-07-15. Critical: 20, High: 40.

Top CVEs affecting Mervinpraison Praisonai
CVESeverityScorePublishedSummary
CVE-2026-61447Critical10.02026-07-11PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python() that executes LLM-generated Python code without AST valid…
CVE-2026-34938Critical10.02026-04-03PraisonAI is a multi-agent teams system. Prior to version 1.5.90, execute_code() in praisonai-agents runs attacker-controlled Python inside a three-layer sandb…
CVE-2026-61445Critical9.92026-07-11PraisonAI before 4.6.78 contains arbitrary file write and command execution vulnerabilities in the AICoder component due to missing path validation and command…
CVE-2026-60090Critical9.82026-07-11PraisonAI before 4.6.78 fails to validate the caller-controlled dimension argument in the PGVector and Cassandra knowledge-store create_collection() backends…
CVE-2026-44335Critical9.82026-05-08PraisonAI is a multi-agent teams system. Prior to version 1.6.32, the URL checking logic in PraisonAI has a logical flaw that could be bypassed by attackers, l…
CVE-2026-41497Critical9.82026-05-08PraisonAI 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 vali…
CVE-2026-40315Critical9.82026-04-14PraisonAI is a multi-agent teams system. Prior to 4.5.133, there is an SQL identifier injection vulnerability in SQLiteConversationStore where the table_prefix…
CVE-2026-40288Critical9.82026-04-14PraisonAI is a multi-agent teams system. In versions below 4.5.139 of PraisonAI and 1.5.140 of praisonaiagents, the workflow engine is vulnerable to arbitrary…
CVE-2026-39890Critical9.82026-04-08PraisonAI is a multi-agent teams system. Prior to 4.5.115, the AgentService.loadAgentFromFile method uses the js-yaml library to parse YAML files without disab…
CVE-2026-34935Critical9.82026-04-03PraisonAI is a multi-agent teams system. From version 4.5.15 to before version 4.5.69, the --mcp CLI argument is passed directly to shlex.split() and forwarded…
CVE-2026-34934Critical9.82026-04-03PraisonAI is a multi-agent teams system. Prior to version 4.5.90, the get_all_user_threads function constructs raw SQL queries using f-strings with unescaped t…
CVE-2026-44336Critical9.62026-05-08PraisonAI is a multi-agent teams system. Prior to version 4.6.34, PraisonAI's MCP (Model Context Protocol) server (praisonai mcp serve) registers four file-han…
CVE-2026-40088Critical9.62026-04-09PraisonAI is a multi-agent teams system. Prior to 4.5.121, the execute_command function and workflow shell execution are exposed to user-controlled input via a…
CVE-2026-40154Critical9.32026-04-09PraisonAI is a multi-agent teams system. Prior to 4.5.128, PraisonAI treats remotely fetched template files as trusted executable code without integrity verifi…
CVE-2026-61444Critical9.12026-07-10PraisonAI versions before 4.6.78 contain a code injection vulnerability in deploy/api.py where the agents_file parameter is directly interpolated into an f-str…
CVE-2026-40313Critical9.12026-04-14PraisonAI 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 le…
CVE-2026-40289Critical9.12026-04-14PraisonAI 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…
CVE-2026-34953Critical9.12026-04-03PraisonAI is a multi-agent teams system. Prior to version 4.5.97, OAuthManager.validate_token() returns True for any token not found in its internal store, whi…
CVE-2026-34952Critical9.12026-04-03PraisonAI is a multi-agent teams system. Prior to version 4.5.97, the PraisonAI Gateway server accepts WebSocket connections at /ws and serves agent topology a…
CVE-2026-39305Critical9.02026-04-07PraisonAI is a multi-agent teams system. Prior to 1.5.113, the Action Orchestrator feature contains a Path Traversal vulnerability that allows an attacker (or…