// Security Advisory Triage

CVE-2026-126681 - Improper restriction of intended endpoints in AWS Labs Timestream for InfluxDB MCP Server

AWS security bulletins · published 2026-11-16 22:00 UTC
ACTION NEEDED VERIFY_EXPOSURE SECURITY
WHAT CHANGEDCVE-2026-126681 - Improper restriction of intended endpoints in AWS Labs Timestream for InfluxDB MCP Server. Source event: 2026-11-16T21:03:04+00:00. RSS discovery: 2026-11-16T21:59:54.516312+00:00.
WHY IT MATTERSThe captured feed identifies CVE-2026-126681. 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/2026-185-aws/ (retrieval attempted 2026-11-16T22:00:54.766Z; RSS discovery 2026-11-16T21:59:54.516312+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
+## CVE-2026-126681 - Improper restriction of intended endpoints in AWS Labs Timestream for InfluxDB MCP Server
+https://aws.amazon.com/security/security-bulletins/rss/2026-185-aws/
+Mon, 16 Nov 2026 21:03:04 +0000
+
+Bulletin ID: 2026-185-AWS Publication Date: 11/16/2026 12:30 PM PST
+Description:
+Improper restriction of intended endpoints in the connection configuration handling of the AWS Labs Timestream for InfluxDB MCP Server (awslabs.timestream-for-influxdb-mcp-server) before 0.0.19 might allow a remote unauthenticated actor (via prompt injection) to obtain the InfluxDB API token configured on the server, sent to a crafted endpoint controlled through an InfluxDB URL introduced in the MCP client context.
+Impacted versions: >=0.0.12 AND <0.0.19
+Refer to the article for the most up-to-date and complete information.
SEPARATE BULLETIN CAPTURE · unavailable

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

retrieval attempted2026-11-16T22:00:54.766Z
captured atunavailable
sourcehttps://aws.amazon.com/security/security-bulletins/2026-185-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 reasoningPrompt injection vulnerability in AWS AI agent framework exposes database credentials to remote unauthenticated actors.
signalsknown exploitation vector: prompt injection · credential theft: InfluxDB API token exposure · remote unauthenticated attack · AI provider SDK/agent framework: MCP Server (Model Context Protocol) · fixed version available: 0.0.19 · affects dependency tree: AWS Labs package in AI/agent workflows
suppression—
triage modelanthropic/claude-haiku-4.5 ($0.00000)
writer modeladvisory-evidence-v2 ($0.00000)