Authenticated tool execution via caller-supplied content block
Published Aug 4, 2026 · Updated Aug 4, 2026
Improper input validation in Amazon Bedrock AgentCore harness before July 31, 2026 allows remote authenticated users to execute configured tools. The InvokeHarness agent event loop dispatches a tool named in a caller-supplied tool-use content block in the final message without model mediation. Access requires authenticated InvokeHarness permissions, and execution is limited to tools configured on that harness; a harness without tools has no tool-execution impact.
Summary
What happened
Improper input validation in Amazon Bedrock AgentCore harness before July 31, 2026 allows remote authenticated users to execute configured tools. The InvokeHarness agent event loop dispatches a tool named in a caller-supplied tool-use content block in the final message without model mediation. Access requires authenticated InvokeHarness permissions, and execution is limited to tools configured on that harness; a harness without tools has no tool-execution impact.
The record
- CVE
- CVE-2026-18830
- Published
- Aug 4, 2026
- Updated
- Aug 4, 2026
- Vendor
- Amazon Web Services
- Product
- Amazon Bedrock AgentCore harness
- Classifications
- CWE-1287
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Aug 4, 2026CVE publishedPublication date reported by the CVE source.
- Aug 4, 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=N/A
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