CVE-2026-43992
Published: 12 May 2026
Summary
CVE-2026-43992 is a critical-severity Exposure of Sensitive Information to an Unauthorized Actor (CWE-200) vulnerability. Its CVSS base score is 9.8 (Critical).
Operationally, it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the Protocol-Specific Risks risk domain.
Threat & Defense Details
Likely Mitigating ControlsAI
Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.
A data action map identifies locations where sensitive information may be exposed to unauthorized actors during processing or transfer.
Encrypting or otherwise protecting data at rest directly prevents unauthorized actors from reading sensitive information stored on disk or other media.
Directly prevents exposure of critical organizational information by applying OPSEC processes across the SDLC.
Literacy training teaches users to recognize and avoid actions that result in unauthorized exposure of sensitive information.
Retaining and monitoring training records confirms personnel have completed privacy and security awareness training on handling sensitive data, reducing the chance of unauthorized exposure due to lack of knowledge.
Monitoring directly detects unauthorized disclosure of sensitive information, enabling response to exposures.
Coordinating audit logging across organizational boundaries reduces the risk of sensitive audit data being exposed to unauthorized actors during transmission.
The control's identification, isolation, alerting, and eradication steps directly limit the impact and exploitation window of unauthorized sensitive information exposure.
NVD Description
JunoClaw is an agentic AI platform built on Juno Network. Prior to 0.x.y-security-1, every MCP write tool (send_tokens, execute_contract, instantiate_contract, upload_wasm, ibc_transfer, etc.) accepted 'mnemonic: string' as an explicit tool-call parameter. The BIP-39 seed was consequently embedded in the LLM…
more
tool-call JSON, exposing it to any transport, log, or telemetry surface in the path between the LLM provider and the MCP process. This vulnerability is fixed in 0.x.y-security-1.
Deeper analysisAI
Automated synthesis unavailable for this CVE.
Details
- CWE(s)
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- Protocol-Specific Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: ai, mcp, llm, llm, mcp