CriticalVulnerability
CVE-2025-62616: AutoGPT server-side request forgery in SendDiscordFileBlock via unfiltered URL
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2025-62616
- Published
- Record updated
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.4%
Summary
CVE-2025-62616 affects AutoGPT, a platform for creating and managing continuous AI agents, prior to autogpt-platform-beta-v0.6.34. In SendDiscordFileBlock, the input URL is passed to aiohttp.ClientSession().get without filtering, which enables a Server-Side Request Forgery (SSRF) flaw. GitHub, Inc. rates it CVSS 4.0 9.3 Critical, with network attack vector, low complexity, no privileges or user interaction, and high confidentiality and integrity impact.
Mitigation
This issue has been patched in autogpt-platform-beta-v0.6.34.
Related items
- MediumCVE-2026-121936: easyVoice server-side request forgery through openaiBaseUrl in /api/v1/ttsSimilar attack · NVD/CVE Database
- MediumCVE-2026-118628: MLflow get-artifacts server-side request forgery information disclosureSimilar attack · NVD/CVE Database
- HighCVE-2026-118625: MLflow Tracking Server privilege escalation via get_endpointsSimilar attack · NVD/CVE Database
- InfoWhen trust becomes the payload: Inside the threats, etc quarterly reportSimilar attack · Elastic Security Labs
- MediumCritical Langflow flaws enable authentication bypass and RCESimilar attack · CSO Online