Raw vector
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:A/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:XSummary
CVE-2026-15746 is a medium-severity SSRF (CWE-918) vulnerability in Amazon (inferred from references). Its CVSS base score is 6.9 (Medium).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 16th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations.
The strongest mitigations our analysis identified map to AC-6 (Least Privilege) and SI-10 (Information Input Validation) — see the control section below for these in your framework.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-44762
Vulnerability Data
Strands Agents is an open-source Python SDK for building and running AI agents. The strands-agents-tools package provides pre-built tools for use with the SDK, including the elasticsearch_memory tool for agent memory storage. We identified CVE-2026-15746, a server-side request forgery (SSRF)…
more
issue in the elasticsearch_memory tool. The tool exposed its connection parameters (es_url, cloud_id, api_key) as fields the large language model (LLM) could control through the tool schema. When a caller omitted the api_key parameter, the tool fell back to the operator's ELASTICSEARCH_API_KEY environment variable and sent it to whichever host the LLM specified. A crafted prompt could cause the tool to connect to a threat-actor-controlled server and disclose the operator's Elasticsearch API key in the Authorization header. We recommend you upgrade to strands-agents-tools version 0.7.0 or later. As a precautionary measure, we recommend all operators rotate their ELASTICSEARCH_API_KEY, even if there is no indication the credential was exposed.
- CWE(s)
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- N/A
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: ai, large language model, llm, llm
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
SSRF vulnerability directly enables exploitation of a public-facing or agent-exposed application (T1190) to steal credentials via crafted requests that leak API keys (T1212).
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
Mitigating Controls (NIST 800-53 r5) AI
Prevents the elasticsearch_memory tool from automatically inheriting and transmitting the ELASTICSEARCH_API_KEY environment variable to an arbitrary host supplied by the LLM.
Requires validation of the untrusted es_url (and cloud_id) parameters before any outbound connection or credential transmission occurs.
Enforces egress filtering or allow-listing so the tool cannot reach an attacker-controlled server even if the LLM supplies a malicious URL.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Secure development practices directly include input validation and destination allow-listing that prevent SSRF.
Runtime monitoring of web applications and services can detect anomalous outbound requests indicative of SSRF.
Vulnerability identification processes can discover and record SSRF flaws in web applications.
Network segmentation and egress controls can limit the damage from successful SSRF requests.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Operational threat data describing SSRF campaigns can be used to tighten outbound-request allow-lists and detection rules before attackers exploit them.