{"id":"CVE-2026-33235","aliases":["EUVD-2026-39090","GHSA-ppw9-h7rv-gwq9"],"status":"published","title":"AutoGPT: Denial of Service (DoS) via Resource Exhaustion in text templating features","description":"AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions prior to 0.6.52, the Fill Text Template block is vulnerable to a Denial of Service (DoS) attack. While the backend implements a SandboxedEnvironment to prevent unauthorized attribute access (e.g., blocking __class__), it fails to limit the computational complexity or execution time of the expressions. An attacker can input computationally expensive Python/Jinja2 expressions that consume the server's CPU and memory, leading to a complete system hang or crash. In multi-tenant or self-hosted environments, this results in a complete service outage and \"noisy neighbor\" effects that require manual administrative intervention to recover. This issue has been fixed in version 0.6.52.","severity":{"version":"3.1","score":7.7,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:N/A:H","level":"high","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-10","score":0.00375,"percentile":0.31797,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":false},"cwes":["CWE-400"],"published":"2026-06-24T20:52:00Z","modified":"2026-10-28T02:30:52Z","products":[{"vendor":"significant-gravitas","product":"autogpt"}],"references":[{"url":"https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-ppw9-h7rv-gwq9","tags":["x_refsource_CONFIRM","exploit","advisory"]},{"url":"https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.52","tags":["x_refsource_MISC","web"]},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/33xxx/CVE-2026-33235.json","tags":["advisory"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-33235","tags":["advisory"]}],"sources":{"cve":[{"id":"CVE-2026-33235","title":"AutoGPT: Denial of Service (DoS) via Resource Exhaustion in text templating features","description":"AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions prior to 0.6.52, the Fill Text Template block is vulnerable to a Denial of Service (DoS) attack. While the backend implements a SandboxedEnvironment to prevent unauthorized attribute access (e.g., blocking __class__), it fails to limit the computational complexity or execution time of the expressions. An attacker can input computationally expensive Python/Jinja2 expressions that consume the server's CPU and memory, leading to a complete system hang or crash. In multi-tenant or self-hosted environments, this results in a complete service outage and \"noisy neighbor\" effects that require manual administrative intervention to recover. This issue has been fixed in version 0.6.52.","status":"published","published":"2026-06-24T20:52:00.388Z","modified":"2026-06-25T15:42:19.793Z","cvss":[{"version":"3.1","score":7.7,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:N/A:H","level":"high","assessor":"cna"}],"cwes":["CWE-400"],"updated_at":"2026-11-02T14:20:08.009733Z"}],"euvd":[{"id":"EUVD-2026-39090","description":"AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions prior to 0.6.52, the Fill Text Template block is vulnerable to a Denial of Service (DoS) attack. While the backend implements a SandboxedEnvironment to prevent unauthorized attribute access (e.g., blocking __class__), it fails to limit the computational complexity or execution time of the expressions. An attacker can input computationally expensive Python/Jinja2 expressions that consume the server's CPU and memory, leading to a complete system hang or crash. In multi-tenant or self-hosted environments, this results in a complete service outage and \"noisy neighbor\" effects that require manual administrative intervention to recover. This issue has been fixed in version 0.6.52.","status":"published","published":"2026-06-24T20:52:00Z","modified":"2026-06-25T15:42:19Z","cvss":[{"version":"3.1","score":7.7,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:N/A:H","level":"high"}],"updated_at":"2026-11-02T18:20:25.700423Z"}],"nvd":[{"id":"CVE-2026-33235","description":"AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions prior to 0.6.52, the Fill Text Template block is vulnerable to a Denial of Service (DoS) attack. While the backend implements a SandboxedEnvironment to prevent unauthorized attribute access (e.g., blocking __class__), it fails to limit the computational complexity or execution time of the expressions. An attacker can input computationally expensive Python/Jinja2 expressions that consume the server's CPU and memory, leading to a complete system hang or crash. In multi-tenant or self-hosted environments, this results in a complete service outage and \"noisy neighbor\" effects that require manual administrative intervention to recover. This issue has been fixed in version 0.6.52.","status":"published","published":"2026-06-24T21:16:53.32Z","modified":"2026-10-25T22:10:00.15Z","cvss":[{"version":"3.1","score":7.7,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:N/A:H","level":"high","assessor":"secondary"}],"cwes":["CWE-400"],"updated_at":"2026-11-02T14:12:25.67873Z"}],"osv":[{"id":"CVE-2026-33235","title":"AutoGPT: Denial of Service (DoS) via Resource Exhaustion in text templating features","description":"AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions prior to 0.6.52, the Fill Text Template block is vulnerable to a Denial of Service (DoS) attack. While the backend implements a SandboxedEnvironment to prevent unauthorized attribute access (e.g., blocking __class__), it fails to limit the computational complexity or execution time of the expressions. An attacker can input computationally expensive Python/Jinja2 expressions that consume the server's CPU and memory, leading to a complete system hang or crash. In multi-tenant or self-hosted environments, this results in a complete service outage and \"noisy neighbor\" effects that require manual administrative intervention to recover. This issue has been fixed in version 0.6.52.","status":"published","published":"2026-06-24T20:52:00.388Z","modified":"2026-10-28T02:30:52.637131553Z","cvss":[{"version":"3.1","score":7.7,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:N/A:H","level":"high"}],"cwes":["CWE-400"],"updated_at":"2026-11-02T15:45:01.548715Z"}]}}