dbcve.org
Information ExposureWeakness · CWE-200

CVE-2026-43992

CRITICAL · 9.8 CVSS v3.1 Published 2026-05-12
Patch available
A vendor patch is available. No clean upgrade release — apply the published patch.
See remediation →
100/100
Remediation priority · Urgent
Remotely reachable No privileges Zero-click Patch available

Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.

NVD · unedited
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 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.

Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.

dbcve analysis · high confidence

The MCP write tools in JunoClaw (send_tokens, execute_contract, instantiate_contract, upload_wasm, ibc_transfer) accepted 'mnemonic: string' as an explicit parameter, causing BIP-39 seed phrases to be embedded in LLM tool-call JSON and exposed to any transport, log, or telemetry surface between the LLM provider and MCP process.

MitigationUpgrade to version 0.x.y-security-1 and rotate any mnemonic phrases that may have been exposed through logs, telemetry, or network traces.

Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.

CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.

From the vector
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.

dbcve checks

Work through these to decide whether this CVE applies to you.

  1. Identify JunoClaw installation and version
    Locate the JunoClaw application or package in your environment. Check its version using 'junoclaw --version', 'pip show junoclaw', or the package manager used for deployment. Compare against the fixed version 0.x.y-security-1.
    Affected if The installed version is prior to the security-patched release and the MCP write tools have been invoked.
  2. Review MCP tool configuration files
    Inspect the configuration files or code that define the MCP tool schemas for JunoClaw. Look for tool definitions of send_tokens, execute_contract, instantiate_contract, upload_wasm, and ibc_transfer. Check if these tools include 'mnemonic' as a declared parameter.
    Affected if The MCP tool schemas contain 'mnemonic: string' as an explicit parameter for any of the five write tools.
  3. Examine LLM tool-call logs or traces
    Search logs, API traces, or telemetry records that capture LLM tool invocation JSON. Look for any instances where the 'arguments' or 'parameters' field contains a BIP-39 seed phrase (typically 12 or 24 words) under a 'mnemonic' key within calls to the affected JunoClaw tools.
    Affected if Log files, transport streams, or telemetry systems contain mnemonic phrases in tool-call data for send_tokens, execute_contract, instantiate_contract, upload_wasm, or ibc_transfer.
  4. Audit historical tool usage
    Review access logs, audit trails, or monitoring dashboards that record MCP tool executions. Identify whether any of the five write tools were called with mnemonic values provided as arguments.
    Affected if Historical records show executions of send_tokens, execute_contract, instantiate_contract, upload_wasm, or ibc_transfer where a mnemonic was passed.

You are affected if JunoClaw version is prior to the security patch AND the MCP write tools (send_tokens, execute_contract, instantiate_contract, upload_wasm, ibc_transfer) were used with an explicit mnemonic parameter, or if mnemonic phrases appear in your logs or telemetry.

Generated from the published advisory. Verify against your own configuration.

Check your environment

Paste your version and any relevant configuration and it will be compared against the affected criteria above. Do not include secrets or credentials.

AI-assisted, checked against the advisory. Informational, not a guarantee.

Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.

dbcve · scoped
Patch available Apply the vendor patch
Vendor patch github.com →
Interim mitigation

Upgrade to version 0.x.y-security-1 and rotate any mnemonic phrases that may have been exposed through logs, telemetry, or network traces.

Recommended fix Moderate confidence

0.x.y-security-1

  1. 1. Review the codebase to identify all MCP write tool implementations that currently accept 'mnemonic: string' as a parameter (send_tokens, execute_contract, instantiate_contract, upload_wasm, ibc_transfer, etc.)
  2. 2. Modify these tools to retrieve the mnemonic from a secure, non-exposed source instead of direct tool-call parameters
  3. 3. Implement a secure configuration or secret management solution (e.g., environment variables, secure vault) to store the BIP-39 seed
  4. 4. Update the MCP tool schemas to remove the 'mnemonic' parameter from all write operations
  5. 5. Ensure the mnemonic is never logged, transmitted, or exposed in any telemetry or transport layer
  6. 6. Review the fix at the vendor commit: https://github.com/Dragonmonk111/junoclaw/commit/339701e
  7. 7. Test all MCP write tools to confirm they function correctly without the mnemonic parameter
  8. 8. Verify no mnemonic strings appear in logs, traces, or network traffic
Caveat May require updates to client integrations that pass mnemonic as a tool parameter

Generated from the published advisory — verify against the referenced sources before acting.

Have this fixed Scoped from the published advisory
  • Consultation4.0 h
  • Implementation16.0 h
  • Testing8.0 h
  • Review / QA4.0 h
32.0 hours of engineering $5,600
Get the patch applied

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $8,960.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-43992 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

Get it on GitHub Scan in the browser

References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.

Primary sources

Practitioner notes

Contributed

Peer-ranked notes from engineers who’ve handled CVE-2026-43992 in production — separate from our analysis above.

No notes yet

Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.

What this is

A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.

What belongs here
  • Verified mitigations, workarounds, and config changes
  • Version or environment caveats, and links to real fixes
  • No weaponised exploit code, or anything meant to cause harm
  • No spam, self-promotion, credentials, or personal data