CVE-2026-56838: falha de alta gravidade em MervinPraison PraisonAI
PraisonAI recipe.run_stream skips dangerous-tool policy enforcement
Publicada em · Atualizada em
Aviso por e-mail quando ela entrar no KEV, ganhar PoC pública ou subir de nota.
21Vexday Risk Score
Sem sinal de exploração. Nenhum artefato público de exploração conhecido até agora.
ssvc Trackcvss 7.8epss 0.1%
PraisonAI is a multi-agent teams system. From version 4.5.87 to before version 4.6.59, PraisonAI recipe execution blocks default-denied dangerous tools unless the caller explicitly passes allow_dangerous_tools=True. The normal recipe.run() path enforces this with _check_tool_policy(). The streaming path, recipe.run_stream(), loads the same recipe, checks dependencies, and then calls _execute_recipe() without running the dangerous-tool policy check. As a result, a recipe that honestly declares execute_command in TEMPLATE.yaml requires.tools is denied by recipe.run(), but reaches the execution engine through recipe.run_stream() with allow_dangerous_tools=False. This issue has been patched in version 4.6.59.
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Produtos afetados
MervinPraison · PraisonAICVEs relacionadas — MervinPraison PraisonAI
No mesmo produto, das mais perigosas para as menos.
CVE-2026-44338HIGHPraisonAI ships and generates a legacy API server with authentication disabled by default, allowing unauthenticated workflow executionEPSS 32.6%CVE-2026-61447CRITICALPraisonAI before 1.6.78 Remote Code Execution via CodeAgentEPSS 15.2%CVE-2026-34938CRITICALPraisonAI: Python Sandbox Escape via str Subclass startswith() Override in execute_codeEPSS 13.4%CVE-2026-48168CRITICALPraisonAI: GitHub Actions Claude workflow command injection via unquoted PR branch nameEPSS 1.5%CVE-2026-47391CRITICALPraisonAI's unauthenticated A2A official example can reach real LLM-driven `eval()` tool executionEPSS 1.5%CVE-2026-57124CRITICALPraisonAI UI MCP connect endpoint allows unauthenticated local command executionEPSS 1.0%