CVE-2026-56838: high-severity vulnerability in MervinPraison PraisonAI
PraisonAI recipe.run_stream skips dangerous-tool policy enforcement
Published · Updated
E-mail alert when it lands in KEV, gets a public PoC or its score goes up.
21Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
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
Affected products
MervinPraison · PraisonAIRelated CVEs — MervinPraison PraisonAI
In the same product, most dangerous first.
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%