Server-Side Request Forgery in AutoGPT by Significant Gravitas
CVE-2025-62616

9.3CRITICAL

Key Information:

Vendor

Significant-gravitas

Status
Autogpt
Vendor
CVE Published:
4 February 2026

What is CVE-2025-62616?

AutoGPT, developed by Significant Gravitas, enables users to create and manage AI agents. A vulnerability exists where the platform's SendDiscordFileBlock feature inadequately filters input URLs due to the direct usage of the aiohttp.ClientSession().get method. This oversight allows potential attackers to exploit the SSRF vulnerability, posing a risk to the integrity of the application and its surrounding network infrastructure. The issue has been addressed in version autogpt-platform-beta-v0.6.34.

Affected Version(s)

AutoGPT < autogpt-platform-beta-v0.6.34

References

https://github.com/Significant-Gravitas/AutoGPT/security/...
x_refsource_CONFIRM

CVSS V4

Score:
9.3
Severity:
CRITICAL
Confidentiality:
High
Integrity:
High
Availability:
None
Attack Vector:
Network
Attack Complexity:
Low
Attack Required:
None
Privileges Required:
Undefined
User Interaction:
None

Timeline

  • Vulnerability published

  • Vulnerability Reserved

.