// Security Advisory Triage

CVE-2026-112380 - Missing authorization in the WhatsApp channel in Kiro Crew

AWS security bulletins · published 2026-10-22 17:13 UTC
ACTION NEEDED VERIFY_EXPOSURE SECURITY
WHAT CHANGEDCVE-2026-112380 - Missing authorization in the WhatsApp channel in Kiro Crew. Source event: 2026-10-20T20:19:42+00:00. RSS discovery: 2026-10-21T22:46:21.333572+00:00.
WHY IT MATTERSThe captured feed identifies CVE-2026-112380. Check exposure against the affected product and versions; detailed remediation evidence is unavailable.
WHAT TO DOCheck your inventory for the product and affected versions named in this advisory. Remediation details were not captured; consult the vendor bulletin before changing configuration or applying a fix. Remediation: see bulletin https://aws.amazon.com/security/security-bulletins/2026-140-aws/ (retrieval attempted 2026-10-22T17:13:10.316Z; RSS discovery 2026-10-21T22:46:21.333572+00:00).
Deterministic source evidence; confidence not scored Primary source ↗ written by advisory-evidence-v2
Show the reasoning — raw diff, triage verdict, confidence
RSS DISCOVERY DIFF
 https://aws.amazon.com/security/security-bulletins/rss/2026-140-aws/
 Tue, 20 Oct 2026 20:19:42 +0000
 
-Bulletin ID: 2026-140-AWS
-
-Scope: AWS
-
-Content Type: Important (requires attention)
-
-Publication Date: 10/20/2026 13:00 PM PDT
+Bulletin ID: 2026-140-AWS Scope: AWS Content Type: Important (requires attention) Publication Date: 10/20/2026 13:00 PM PDT
 Description:
 Kiro Crew is an open-source personal AI agent that can be reached from a web dashboard, a CLI, or messaging channels such as WhatsApp, and that runs tools on the operator's machine.
 We identified CVE-2026-112380, an authorization issue in the WhatsApp channel and the internal subagent run-control endpoints. In certain configurations where a WhatsApp group was added to an operator's allowed groups, or where the direct-message policy was set to open, a member of that WhatsApp group could send instructions to another session's subagent. The subagent then executed those instructions on the operator's machine under that session's approval policy, and the resulting audit trail was attributed to the operator rather than the actual sender.
SEPARATE BULLETIN CAPTURE · unavailable

Retrieved separately from the RSS discovery; this does not establish historical page content.

retrieval attempted2026-10-22T17:13:10.316Z
captured atunavailable
sourcehttps://aws.amazon.com/security/security-bulletins/2026-140-aws/
content SHA-256unavailable
bulletin retrieval or evidence validation failed
HOW IT WAS JUDGED
Triage signals below are model-reported assertions, preserved verbatim; they are not independent arithmetic verification.
triage verdictMATERIAL at 0.92, needed 0.55
triage reasoningAuthorization bypass in open-source AI agent framework allows unauthenticated command execution and audit evasion.
signalsCVE identifier present (CVE-2026-112380) · authorization bypass in agent framework · cross-session command execution on operator machine · audit trail spoofing (attribution forgery) · affects AI agent SDK/framework in dependency tree · multi-channel attack surface (WhatsApp, CLI, web dashboard)
suppression—
triage modelanthropic/claude-haiku-4.5 ($0.00000)
writer modeladvisory-evidence-v2 ($0.00000)