Credential disclosure via LLM-controlled connection destination
Published Jul 15, 2026 · Updated Jul 15, 2026
SSRF in Strands Agents Tools before 0.7.0 allows remote attackers to disclose an operator's Elasticsearch API key via a crafted prompt. The elasticsearch_memory tool lets the LLM select es_url while an omitted api_key falls back to ELASTICSEARCH_API_KEY and sends it to that host in the Authorization header. Exploitation requires prompt influence, use of the tool, an exposed environment credential, and outbound access to an attacker-controlled server.
Summary
What happened
SSRF in Strands Agents Tools before 0.7.0 allows remote attackers to disclose an operator's Elasticsearch API key via a crafted prompt. The elasticsearch_memory tool lets the LLM select es_url while an omitted api_key falls back to ELASTICSEARCH_API_KEY and sends it to that host in the Authorization header. Exploitation requires prompt influence, use of the tool, an exposed environment credential, and outbound access to an attacker-controlled server.
The record
- CVE
- CVE-2026-15746
- Published
- Jul 15, 2026
- Updated
- Jul 15, 2026
- Vendor
- Amazon Web Services
- Product
- Strands Agents Tools
- Classifications
- CWE-918, T1528
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jul 15, 2026CVE publishedPublication date reported by the CVE source.
- Jul 15, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0 <0.7.0
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo