CVE-2025-53944
AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.45%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
Description
AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents. In v0.6.15 and below, the external API's get_graph_execution_results endpoint has an authorization bypass vulnerability. While it correctly validates user access to the graph_id, it fails to verify ownership of the graph_exec_id parameter, allowing authenticated users to access any execution results by providing arbitrary execution IDs. The internal API implements proper validation for both parameters. This is fixed in v0.6.16.
- CVSS 3.1
- 7.7 HIGHCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N
- EPSS
- 0.45% probability · 38th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-285, CWE-639
- Affected
- agpt/autogpt platform
- Source
- security-advisories@github.com
References
- https://github.com/Significant-Gravitas/AutoGPT/commit/309114a727baa2063357810d444e9a119f8dd7f6Patch
- https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.16Release Notes
- https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-x77j-qg2x-fgg6Exploit, Vendor Advisory
- https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-x77j-qg2x-fgg6Exploit, Vendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.