CVE-2026-65699

AgentGPT through 1.0.0 contains an authorization bypass through user-controlled key vulnerability that allows authenticated users to attach tasks to another user's agent run by supplying a target run_id in the request body without ownership verification. The AgentCRUD.create_task and validate_task_count functions look up the target AgentRun using the client-supplied run_id without confirming the run belongs to the requesting user, enabling an attacker who obtains a valid run_id to corrupt task history, exhaust the per-run loop budget, and drive LLM costs against the victim's run.

CVSS v3 4.2 MEDIUM

4.2^/10

CVSS v3 : MEDIUM

Vector :

Exploitability : 1.6 / Impact : 2.5

Attack Vector NETWORK

Attack Complexity HIGH

Privileges Required LOW

User Interaction NONE

Confidentiality Impact NONE

Integrity Impact LOW

Availability Impact LOW

Scope UNCHANGED

References

Link	Resource
https://github.com/geo-chen/oss/blob/main/AgentGPT.md
https://www.vulncheck.com/advisories/agentgpt-authorization-bypass-via-agent-task-creation

Configurations

No configuration.

History

No history.

Information

Published : 2026-07-23 18:17

Updated : 2026-07-23 19:17

NVD link : CVE-2026-65699

Mitre link : CVE-2026-65699

CVE.ORG link : CVE-2026-65699

JSON object : View

Products Affected

No product.

CWE

CWE-639

Authorization Bypass Through User-Controlled Key

{"id": "CVE-2026-65699", "cveTags": [{"tags": ["unsupported-when-assigned"], "sourceIdentifier": "disclosure@vulncheck.com"}], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-65699", "role": "CISA Coordinator", "options": [{"exploitation": "none"}, {"automatable": "no"}, {"technicalImpact": "partial"}], "version": "2.0.3", "timestamp": "2026-07-23T18:17:18.104555Z"}}], "cvssMetricV31": [{"type": "Secondary", "source": "disclosure@vulncheck.com", "cvssData": {"scope": "UNCHANGED", "version": "3.1", "baseScore": 4.2, "attackVector": "NETWORK", "baseSeverity": "MEDIUM", "vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:L", "integrityImpact": "LOW", "userInteraction": "NONE", "attackComplexity": "HIGH", "availabilityImpact": "LOW", "privilegesRequired": "LOW", "confidentialityImpact": "NONE"}, "impactScore": 2.5, "exploitabilityScore": 1.6}], "cvssMetricV40": [{"type": "Secondary", "source": "disclosure@vulncheck.com", "cvssData": {"Safety": "NOT_DEFINED", "version": "4.0", "Recovery": "NOT_DEFINED", "baseScore": 2.3, "Automatable": "NOT_DEFINED", "attackVector": "NETWORK", "baseSeverity": "LOW", "valueDensity": "NOT_DEFINED", "vectorString": "CVSS:4.0/AV:N/AC:H/AT:N/PR:L/UI:N/VC:N/VI:L/VA:L/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X", "exploitMaturity": "NOT_DEFINED", "providerUrgency": "NOT_DEFINED", "userInteraction": "NONE", "attackComplexity": "HIGH", "attackRequirements": "NONE", "privilegesRequired": "LOW", "subIntegrityImpact": "NONE", "vulnIntegrityImpact": "LOW", "integrityRequirement": "NOT_DEFINED", "modifiedAttackVector": "NOT_DEFINED", "subAvailabilityImpact": "NONE", "vulnAvailabilityImpact": "LOW", "availabilityRequirement": "NOT_DEFINED", "modifiedUserInteraction": "NOT_DEFINED", "modifiedAttackComplexity": "NOT_DEFINED", "subConfidentialityImpact": "NONE", "vulnConfidentialityImpact": "NONE", "confidentialityRequirement": "NOT_DEFINED", "modifiedAttackRequirements": "NOT_DEFINED", "modifiedPrivilegesRequired": "NOT_DEFINED", "modifiedSubIntegrityImpact": "NOT_DEFINED", "modifiedVulnIntegrityImpact": "NOT_DEFINED", "vulnerabilityResponseEffort": "NOT_DEFINED", "modifiedSubAvailabilityImpact": "NOT_DEFINED", "modifiedVulnAvailabilityImpact": "NOT_DEFINED", "modifiedSubConfidentialityImpact": "NOT_DEFINED", "modifiedVulnConfidentialityImpact": "NOT_DEFINED"}}]}, "affected": [{"source": "disclosure@vulncheck.com", "affectedData": [{"repo": "https://github.com/reworkd/AgentGPT", "vendor": "reworkd", "product": "AgentGPT", "versions": [{"status": "affected", "version": "0", "versionType": "semver", "lessThanOrEqual": "1.0.0"}], "packageURL": "pkg:github/reworkd/AgentGPT", "defaultStatus": "affected"}]}], "published": "2026-07-23T18:17:01.153", "references": [{"url": "https://github.com/geo-chen/oss/blob/main/AgentGPT.md", "source": "disclosure@vulncheck.com"}, {"url": "https://www.vulncheck.com/advisories/agentgpt-authorization-bypass-via-agent-task-creation", "source": "disclosure@vulncheck.com"}], "vulnStatus": "Deferred", "weaknesses": [{"type": "Secondary", "source": "disclosure@vulncheck.com", "description": [{"lang": "en", "value": "CWE-639"}]}], "descriptions": [{"lang": "en", "value": "AgentGPT through 1.0.0 contains an authorization bypass through user-controlled key vulnerability that allows authenticated users to attach tasks to another user's agent run by supplying a target run_id in the request body without ownership verification. The AgentCRUD.create_task and validate_task_count functions look up the target AgentRun using the client-supplied run_id without confirming the run belongs to the requesting user, enabling an attacker who obtains a valid run_id to corrupt task history, exhaust the per-run loop budget, and drive LLM costs against the victim's run."}], "lastModified": "2026-07-23T19:17:05.160", "sourceIdentifier": "disclosure@vulncheck.com"}