CVE-2026-72922— AutoGPT: Webhook provider path confusion bypasses generic webhook secret verification
Possible ATT&CK Techniques 3AI
T1059 · Command and Scripting Interpreter T1136 · Create Account T1190 · Exploit Public-Facing ApplicationAffected Version Matrix 1
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| Significant-Gravitas | AutoGPT | < 0.6.70 | affected |
Get alerts for future matching vulnerabilitiesLog in to subscribe
I. Basic Information for CVE-2026-72922
Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗ Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.
Vulnerability Title
AutoGPT: Webhook provider path confusion bypasses generic webhook secret verification
Source: CVE Program / CVE List V5
Vulnerability Description
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.70, AutoGPT's autogpt_platform/backend/backend/api/features/integrations/router.py webhook_ingress_generic route selected get_webhook_manager(provider) from the untrusted provider URL segment without verifying webhook.provider, allowing a request to /compass/webhooks/{webhook_id}/ingress to use CompassWebhookManager's inherited no-op BaseWebhooksManager.verify_signature instead of GenericWebhooksManager.verify_signature, bypass X-Webhook-Secret for a configured secret_token, and execute a generic webhook graph as its owner. This issue is fixed in version 0.6.70.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:H/A:N
Source: CVE Program / CVE List V5
Vulnerability Type
认证机制不恰当
Source: CVE Program / CVE List V5
Affected Products
| Vendor | Product | Affected Versions | CPE | Subscribe |
|---|---|---|---|---|
| Significant-Gravitas | AutoGPT | < 0.6.70 | - |
II. Public POCs for CVE-2026-72922
| # | POC Description | Source Link | Shenlong Link |
|---|
AI-Generated POCVerified env Premium
Reproduced successfully in a real sandbox· Below is the actual recording of building the environment and exploiting the vulnerability.
Reproduction recording is a Pro+ exclusive
Watch the full sandbox build + live exploit recording for this CVE. Limited-time ¥499/mo.
Upgrade to Pro+claude_code · 7007 chars
Pro+ exclusive includes:
Vulnerability reproduction recording (real sandbox build + trigger, exclusive)
In-depth vulnerability mechanism
Trigger conditions & impact
Full executable POC code
Exploit chain & mitigation
POC zip download
100+ AI POC generations per month
III. Intelligence Information for CVE-2026-72922
请登录查看更多情报信息。
Patches & Fixes for CVE-2026-72922 (2)
Vendor Advisories for CVE-2026-72922 (1)
Vendor Pages for CVE-2026-72922 (1)
IV. Related Vulnerabilities
Same product: AutoGPT
- CVE-2025-32394
AutoGPT: There is a DoS vulnerability in AITextSummarizerBlo - CVE-2025-32423
AutoGPT: There is a DoS vulnerability in ExtractTextInformat - CVE-2026-56663
AutoGPT: SSRF-to-RCE Chain in `SendWebRequestBlock` via IP v - CVE-2026-56823
AutoGPT: IDOR in Webhook Ping Endpoint Allows Enumeration an - CVE-2026-33235
AutoGPT: Denial of Service (DoS) via Resource Exhaustion in
Same vendor: Significant-Gravitas
- CVE-2025-32394
AutoGPT: There is a DoS vulnerability in AITextSummarizerBlo - CVE-2025-32423
AutoGPT: There is a DoS vulnerability in ExtractTextInformat - CVE-2026-56663
AutoGPT: SSRF-to-RCE Chain in `SendWebRequestBlock` via IP v - CVE-2026-56823
AutoGPT: IDOR in Webhook Ping Endpoint Allows Enumeration an - CVE-2026-33235
AutoGPT: Denial of Service (DoS) via Resource Exhaustion in
Same weakness: CWE-287
- CVE-2026-59500
Priority - CWE-287: Improper Authentication - CVE-2026-47718
FUXA provides guest and invalid-token access to protected re - CVE-2026-73501
kin-openapi: ValidationHandler.Load() Fail-Open Authenticati - CVE-2024-27253
IBM Engineering Requirements Management DOORS Next is impact - CVE-2026-12359
Security vulnerabilities have been found in IBM Verify Ident
V. Comments for CVE-2026-72922
No comments yet