Vulnerability in AutoGPT (CVE-2026-45023)
Summary
Vulnerability in AutoGPT (CVE-2026-45023). Risk of unauthorized operations or information disclosure. Exploitable via POST /api/blocks/{block_id}/execute. Mitigation: upgrade to 0.6.59 or later.
Original description
The description as published by the source.
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.59, POST /api/blocks/{block_id}/execute endpoint executes blocks without consuming any credits, regardless of the user's balance. The credit check that exists in the graph execution path (manager.py) is never reached when blocks are called directly via the external API, allowing unlimited free execution of all blocks. This vulnerability is fixed in 0.6.59.
Source: NIST National Vulnerability Database NVD
Auto-generated summary
Assembled by SecPulse from the source data (CVSS, CWE, affected versions) using templates — no AI involved. Check the original description and references below for exact details.
A vulnerability tracked as CVE-2026-45023 has been found in AutoGPT.
Attackers can target a specific entry point like POST /api/blocks/{block_id}/execute over the network to misuse the product.
Risk of unauthorized operations or information disclosure. CVSS score: 5.4/10.
What to do: upgrade AutoGPT to 0.6.59 or later.
If unsure, ask your IT team or search "AutoGPT CVE-2026-45023" on the vendor's site.
CVE-2026-45023 (AutoGPT) — CWE-770 / CVSS v3 5.4
Attack vector: remote (network-reachable) / no user interaction
Attack surface: POST /api/blocks/{block_id}/execute
Patched: 0.6.59 — apply immediately
Plan: 1) Audit SBOM/dependencies, 2) Stage→prod upgrade, 3) Add WAF/proxy monitoring on affected endpoints, 4) Hunt IOCs in logs.
Refs: see the GHSA / vendor advisory / patched release linked on this page.
A vulnerability (CWE-770) exists in AutoGPT. Attackers reach the vulnerable code path via POST /api/blocks/{block_id}/execute.
Check the vendor advisory for the affected versions of AutoGPT. Attack surface: POST /api/blocks/{block_id}/execute.
Severity: Medium (CVSS 5.4/10). Risk of unauthorized operations or information disclosure.
Update to 0.6.59.
Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.
Search webserver/proxy logs for unusual POST /api/blocks/{block_id}/execute requests with malformed payloads or SQL meta-characters. Run grep -r 'AutoGPT' . against your dependency files (package-lock.json, requirements.txt, go.sum) to find affected services.
Response actions
Concrete steps and command examples for SOC/SRE teams to execute in order
-
1Identify exposure identify
grep -r 'AutoGPT' . | grep -v node_modulesリポジトリと本番環境の依存ファイル (package-lock.json / requirements.txt / go.sum / Gemfile.lock 等) で
AutoGPTを grep し、稼働しているサービス・バージョンを把握する。 -
2Hunt for indicators of compromise detect
grep 'POST /api/blocks/{block_id}/execute' /var/log/nginx/access.log | grep -E '(unusual_payload|sqli_pattern)'アクセスログで
POST /api/blocks/{block_id}/executeへの異常なリクエスト (不正な認証ヘッダ・SQLメタ文字)を過去 30〜90日分捜索。WAF/SIEM があれば該当パスのアラート発火履歴を確認。 -
3Apply patch patch
Upgrade AutoGPT to 0.6.59ステージング環境で 0.6.59 に上げて回帰テスト → 本番反映。回帰テストはアプリの主要ハッピーパスと、Step 2 で見つけた異常検知の続報チェックを含めること。
-
4Post-deployment verification verify
Replay attack against POST /api/blocks/{block_id}/execute on staging to confirm patch closes the vectorパッチ適用後、ステージングで PoC または同等の悪用パターンを再現して脆弱性が閉じたことを確認。本番では Step 2 と同じログクエリでアラート再発が無いか継続監視。
References
- web github.com