CVE-2025-53944

AutoGPT Platform Exposes Graph Execution Results via Authorization Gap

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.

Affected

Significant-Gravitas · AutoGPT

CVSS v3.1 NVD

7.7 HIGHCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N

EPSS

0.46% chance of exploitation in the next 30 days, 39th percentile

Published

2025-07-30

Proof-of-concept exploits (1)

• Significant-Gravitas/AutoGPT/security/advisories/GHSA-x77j-qg2x-fgg6

Security advisories

• Significant-Gravitas/AutoGPT/commit/309114a727baa2063357810d444e9a119f8dd7f6

References

• CVE Record
• NVD entry