CVE-2026-56838

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 v3 7.8 HIGH

7.8^/10

CVSS v3 : HIGH

Vector :

Exploitability : 1.8 / Impact : 5.9

Attack Vector LOCAL

Attack Complexity LOW

Privileges Required NONE

User Interaction REQUIRED

Confidentiality Impact HIGH

Integrity Impact HIGH

Availability Impact HIGH

Scope UNCHANGED

References

Link	Resource
https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-v847-hxxw-3pxg
https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-v847-hxxw-3pxg

Configurations

No configuration.

History

29 Oct 2026, 14:17

Type	Values Removed	Values Added
References	~~() https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-v847-hxxw-3pxg -~~	() https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-v847-hxxw-3pxg -

23 Oct 2026, 12:18

Type	Values Removed	Values Added
New CVE

Information

Published : 2026-10-23 12:18

Updated : 2026-10-29 14:17

NVD link : CVE-2026-56838

Mitre link : CVE-2026-56838

CVE.ORG link : CVE-2026-56838

JSON object : View

Products Affected

No product.

CWE

CWE-78

Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')

CWE-693

Protection Mechanism Failure

CWE-863

Incorrect Authorization

{"id": "CVE-2026-56838", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-56838", "role": "CISA Coordinator", "options": [{"exploitation": "poc"}, {"automatable": "no"}, {"technicalImpact": "total"}], "version": "2.0.3", "timestamp": "2026-10-29T13:52:31.231130Z"}}], "cvssMetricV31": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 7.8, "attackVector": "LOCAL", "baseSeverity": "HIGH", "vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H", "integrityImpact": "HIGH", "userInteraction": "REQUIRED", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "NONE", "confidentialityImpact": "HIGH"}, "impactScore": 5.9, "exploitabilityScore": 1.8}]}, "affected": [{"source": "security-advisories@github.com", "affectedData": [{"vendor": "MervinPraison", "product": "PraisonAI", "versions": [{"status": "affected", "version": ">= 4.5.87, < 4.6.59"}]}]}], "published": "2026-10-23T12:18:15.357", "references": [{"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-v847-hxxw-3pxg", "source": "security-advisories@github.com"}, {"url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-v847-hxxw-3pxg", "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0"}], "vulnStatus": "Deferred", "weaknesses": [{"type": "Secondary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-78"}, {"lang": "en", "value": "CWE-693"}, {"lang": "en", "value": "CWE-863"}]}], "descriptions": [{"lang": "en", "value": "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."}], "lastModified": "2026-10-29T14:17:57.370", "sourceIdentifier": "security-advisories@github.com"}