CVE-2026-15746
MediumCVSS 6.5Exploitation Probability (EPSS)
Low risk36th percentile - higher than 36% of all known CVEs
Summary
A server-side request forgery (SSRF) vulnerability was found in the elasticsearch_memory tool of the strands-agents-tools package. Connection parameters (es_url, cloud_id, api_key) were controllable by the LLM, and omitting api_key caused the operator's API key to be sent to any host specified by the LLM.
Risk Assessment
An attacker can craft a prompt to steal the operator's Elasticsearch API key, leading to unauthorized data access and potential further compromise of the infrastructure.
Recommendation
Upgrade strands-agents-tools to version 0.7.0 or later and rotate the ELASTICSEARCH_API_KEY as a precaution, even if no exposure is detected.
Other vulnerabilities in strands-agents-tools
See all- CVE-2026-115415Medium
Improper neutralization of input used for LLM prompting in the environment tool in Strands Agents Tools before 0.8.6 might allow remote actors to obtain the agent host's environment variables in cleartext, including cloud credentials and API keys, via a crafted prompt that disables the tool's secret masking. To remediate this issue, users should upgrade to version 0.8.6 or later and rotate any credentials that were present in the environment of agents that loaded the environment tool.
- CVE-2026-18394High
In Strands Agents Tools before 0.8.2, incorrect authorization in the http_request tool may allow remote attackers to obtain credentials configured via HTTP_REQUEST_TOKEN_CONFIG by influencing the LLM to route requests through attacker-controlled proxy infrastructure.
Original NVD description (English source)
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) 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.
Vulnerability data from NVD (NIST) · CISA KEV · EPSS