Detection queries Vulnerability reportAgents & MCP · Windows

mcp-remote OAuth authorization_endpoint RCE (CVE-2025-6514)

A malicious or intercepted MCP server could return a crafted OAuth URL that runs commands through PowerShell on Windows. CVSS 9.6; fixed in mcp-remote 0.1.16.

What happened

Critical OS command injection in mcp-remote 0.0.5–0.1.15. Malicious or MITM MCP server returns crafted OAuth authorization_endpoint; client opens URL and on Windows PowerShell executes injected commands. CVSS 9.6. Fixed in 0.1.16.

Read the original sourceAdditional source: github.comAdditional source: nvd.nist.gov

How it happened

Select a stage to explore its defenses MagicSword policy opportunity
Detect this stage
Detect this stage
MagicSword Detect this stage
Detect this stage
Select a stage · Drag to explore · + / − to zoom · Dashed edges are loopsSelect a stage · Arrows show reported connectionsReported sequence
Read the flow as text & sources

A catalog reconstruction of the supplied source account. Unknown steps remain explicit; an edge describes the reported relationship between steps.

  1. 01 · Client connects to an untrusted server

    An attacker-controlled, compromised or intercepted remote MCP connection is used.

    Hunt: A repository, dependency or agent changes MCP commands, automatic-task settings, tool approval or model-routing configuration before new execution.

    A file-write event alone cannot establish what changed. Legitimate setup also changes these files; obtain a diff and authorization context.

    Source for step 1
  2. 02 · Server returns OAuth discovery data

    The response supplies a crafted authorization_endpoint URL.

    Hunt: Untrusted content or a changed tool definition precedes a file read, command, or remote call outside the user's intended task.

    Process logs cannot recover model intent. Remote connectors and in-process interpreters may produce no local child process. Prompt content alone is not a reliable signature.

    Source for step 2
  3. 03 · Browser-opening helper invokes PowerShell

    On affected Windows clients the URL is interpreted as a command-injection payload.

    Hunt: A script host or shell runs encoded content, a remote URL, or inline script syntax, then downloads or launches a payload.

    Encoded commands and remote administration can be legitimate. This does not cover every script host, in-process execution, or non-Windows branch.

    MagicSword policy opportunity · Windows clients with an enforced policy restricting the helper; update mcp-remote as the primary remediation.

    Source for step 3
  4. 04 · Commands execute locally

    Affected mcp-remote versions permit OS command execution; the report identifies a fixed version.

    Hunt: A script host or shell runs encoded content, a remote URL, or inline script syntax, then downloads or launches a payload.

    Encoded commands and remote administration can be legitimate. This does not cover every script host, in-process execution, or non-Windows branch.

    Source for step 4

Why it matters

Reported entry point: Connect mcp-remote client to untrusted/compromised remote MCP server. Reported impact: Affected mcp-remote versions permit OS command execution; the report identifies a fixed version.

Check these source-linked conditions against your setup.

mcp-remoteWindowsMCP connection required

mcp-remote is the affected MCP client in the source account.

Conditions to check
  • Confirm that the installed version is affected by the historical report; selecting a product does not establish its version or patch status.
  • The reported command-injection path depends on Windows OAuth URL handling and an untrusted remote MCP server.

Source-linked applicability guidance. Confirm current scope in the original report.

Read the original report

What you can do

Protection & prevention

Start here

Check the vendor advisory and update the affected client; review remote MCP OAuth destinations.

Upgrade mcp-remote ≥0.1.16; argv not shell for URLs; trust only pinned MCP origins

Catalog defensive guidance based on the reported behavior. Confirm scope and current mitigations in the original source.

Review the original guidance Additional source 2 Additional source 3
Explore scoped MagicSword policy options

Requires an enforced Windows policy covering the actual executable. Audit mode records events without blocking.

Restrict an unsafe execution helper

Use MagicSword application control to restrict an unneeded Windows shell/helper or deny unapproved payloads while the vulnerable client is patched.

Applies to: Windows clients with an enforced policy restricting the helper; update mcp-remote as the primary remediation.

Policy opportunity, not tested incident coverage. Requires enrolled Windows devices, a policy covering the actual executable, and enforcement. Audit mode records decisions without blocking; allowed tools and in-process / cloud actions can remain reachable.

Explore the policy control View mapped attack stage
Investigate each phase

Detection queries

Draft query starters grouped by the attack stages where they apply.

Download stage pack

Start with the logs you collect. Each hunt identifies its required visibility, field mapping and limits. Queries are catalog-authored drafts using reusable behavior profiles; test with known activity and your normal baseline before alerting.

01Client connects to an untrusted serverAgent trust / configuration changesCustom schema · Draft

An attacker-controlled, compromised or intercepted remote MCP connection is used.

What to look for

A repository, dependency or agent changes MCP commands, automatic-task settings, tool approval or model-routing configuration before new execution.

Review server origin and connection configuration against the approved inventory; a remote connection alone is not exploitation.

Visibility: Defender-side logs where collected

Required logs

  • File changes and before/after content for MCP / IDE configuration
  • Repository audit / pull-request history
  • Agent startup and tool-invocation logs

Coverage limit. A file-write event alone cannot establish what changed. Legitimate setup also changes these files; obtain a diff and authorization context.

Custom-schema candidates, not out-of-box detectors. Map your application / cloud / platform logs to EventType, Actor, Asset, Action, Target and CorrelationId. KQL uses a custom OpenAttacksAudit_CL table; SPL uses openattacks:audit. EventType values are proposed normalization names, not native vendor event names. Correlation and environment-specific alert logic remain to be built.

Sigma
Draft SigmaDownload Sigma
title: Hunt - Agent trust / configuration changes
id: 2dfc8034-d66b-42a7-a699-a76b2ef872ac
status: experimental
description: A repository, dependency or agent changes MCP commands,
  automatic-task settings, tool approval or model-routing configuration before
  new execution.
author: MagicSword OpenAttacks catalog
date: 2026-10-23
falsepositives:
  - Authorized activity matching this broad hunt; baseline and investigate
    before alerting.
level: low
logsource:
  category: application
  product: openattacks_audit
  definition: Custom normalized audit schema; map EventType, Actor, Asset, Action,
    Target and CorrelationId from the required source logs first.
detection:
  selection:
    EventType:
      - agent.config.write
      - agent.approval.change
  condition: selection
KQL
Draft KQLDownload KQL
// SCHEMA TEMPLATE: create/map this custom table before use; not a built-in Sentinel table.
// OpenAttacksAudit_CL: TimeGenerated(datetime), EventType/Actor/Asset/Action/Target/CorrelationId(string).
// Selects candidates only. Apply the stage hypothesis and correlation steps before alerting.
OpenAttacksAudit_CL
| where TimeGenerated > ago(7d)
| where EventType in ("agent.config.write", "agent.approval.change")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated desc
SPL
Draft SPLDownload SPL
sourcetype="openattacks:audit"
EventType IN ("agent.config.write", "agent.approval.change")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _time
Investigation steps
  1. Diff command, args, environment, origin, autoApprove and task settings against the previously approved version.
  2. Correlate the author and change with the next agent launch; inspect path canonicalization and trailing-dot variants where relevant.
02Server returns OAuth discovery dataUnexpected agent tool useCustom schema · Draft

The response supplies a crafted authorization_endpoint URL.

What to look for

Untrusted content or a changed tool definition precedes a file read, command, or remote call outside the user's intended task.

Visibility: Defender-side logs where collected

Required logs

  • Agent tool-call audit records with session / tool / destination
  • Tool-definition and approval changes
  • Endpoint process, file-access and network evidence where available

Coverage limit. Process logs cannot recover model intent. Remote connectors and in-process interpreters may produce no local child process. Prompt content alone is not a reliable signature.

Custom-schema candidates, not out-of-box detectors. Map your application / cloud / platform logs to EventType, Actor, Asset, Action, Target and CorrelationId. KQL uses a custom OpenAttacksAudit_CL table; SPL uses openattacks:audit. EventType values are proposed normalization names, not native vendor event names. Correlation and environment-specific alert logic remain to be built.

Sigma
Draft SigmaDownload Sigma
title: Hunt - Unexpected agent tool use
id: c709e384-0e11-479e-ab4d-3a06e2431e4b
status: experimental
description: Untrusted content or a changed tool definition precedes a file
  read, command, or remote call outside the user's intended task.
author: MagicSword OpenAttacks catalog
date: 2026-10-23
falsepositives:
  - Authorized activity matching this broad hunt; baseline and investigate
    before alerting.
level: low
logsource:
  category: application
  product: openattacks_audit
  definition: Custom normalized audit schema; map EventType, Actor, Asset, Action,
    Target and CorrelationId from the required source logs first.
detection:
  selection:
    EventType:
      - agent.tool.call
      - agent.tool.definition.change
  condition: selection
KQL
Draft KQLDownload KQL
// SCHEMA TEMPLATE: create/map this custom table before use; not a built-in Sentinel table.
// OpenAttacksAudit_CL: TimeGenerated(datetime), EventType/Actor/Asset/Action/Target/CorrelationId(string).
// Selects candidates only. Apply the stage hypothesis and correlation steps before alerting.
OpenAttacksAudit_CL
| where TimeGenerated > ago(7d)
| where EventType in ("agent.tool.call", "agent.tool.definition.change")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated desc
SPL
Draft SPLDownload SPL
sourcetype="openattacks:audit"
EventType IN ("agent.tool.call", "agent.tool.definition.change")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _time
Investigation steps
  1. Join input provenance, tool descriptions and calls by session ID and compare the action to the approved task.
  2. Inspect child processes and destinations; record whether execution was in-process, local, or through a remote SaaS connector.
03Browser-opening helper invokes PowerShellSuspicious Windows script executionNative logs · Draft

On affected Windows clients the URL is interpreted as a command-injection payload.

What to look for

A script host or shell runs encoded content, a remote URL, or inline script syntax, then downloads or launches a payload.

Visibility: Defender-side logs where collected

Required logs

  • Windows process creation: Sysmon Event 1 or Defender DeviceProcessEvents
  • PowerShell script-block logging when enabled
  • Download / network and installer events

Coverage limit. Encoded commands and remote administration can be legitimate. This does not cover every script host, in-process execution, or non-Windows branch.

Windows process candidates. Sigma uses normalized process_creation fields; KQL requires Defender for Endpoint; SPL requires the Sysmon XML sourcetype. Tune collectors, fields and baselines before use.

Sigma
Draft SigmaDownload Sigma
title: Hunt - Suspicious Windows script execution
id: 2bb88802-9f03-4d99-a192-fe44c9484e8b
status: experimental
description: A script host or shell runs encoded content, a remote URL, or
  inline script syntax, then downloads or launches a payload.
author: MagicSword OpenAttacks catalog
date: 2026-10-23
falsepositives:
  - Authorized activity matching this broad hunt; baseline and investigate
    before alerting.
level: low
logsource:
  category: process_creation
  product: windows
detection:
  selection:
    Image|endswith:
      - \powershell.exe
      - \pwsh.exe
      - \mshta.exe
      - \wscript.exe
      - \cscript.exe
    CommandLine|contains:
      - -enc
      - http
      - FromBase64String
      - "javascript:"
      - "vbscript:"
  condition: selection
KQL
Draft KQLDownload KQL
// Draft hunt; requires Defender for Endpoint process telemetry for this OS.
DeviceProcessEvents
| where Timestamp > ago(7d)
| where FileName in~ ("powershell.exe", "pwsh.exe", "mshta.exe", "wscript.exe", "cscript.exe")
| where ProcessCommandLine contains "-enc" or ProcessCommandLine contains "http" or ProcessCommandLine contains "FromBase64String" or ProcessCommandLine contains "javascript:" or ProcessCommandLine contains "vbscript:"
| project Timestamp, DeviceName, AccountName, FileName, ProcessCommandLine, InitiatingProcessFileName, InitiatingProcessCommandLine, SHA1
| order by Timestamp desc
SPL
Draft SPLDownload SPL
sourcetype="XmlWinEventLog:Microsoft-Windows-Sysmon/Operational" EventCode=1
Image IN ("*\\powershell.exe", "*\\pwsh.exe", "*\\mshta.exe", "*\\wscript.exe", "*\\cscript.exe")
CommandLine IN ("*-enc*", "*http*", "*FromBase64String*", "*javascript:*", "*vbscript:*")
| table _time host User Image CommandLine ParentImage ParentCommandLine
| sort - _time
Investigation steps
  1. Follow the parent and child process tree and recover the script or URL from logs without executing it.
  2. Correlate the payload's signer/hash, persistence, and network activity; baseline approved automation.
04Commands execute locallySuspicious Windows script executionNative logs · Draft

Affected mcp-remote versions permit OS command execution; the report identifies a fixed version.

What to look for

A script host or shell runs encoded content, a remote URL, or inline script syntax, then downloads or launches a payload.

Visibility: Defender-side logs where collected

Required logs

  • Windows process creation: Sysmon Event 1 or Defender DeviceProcessEvents
  • PowerShell script-block logging when enabled
  • Download / network and installer events

Coverage limit. Encoded commands and remote administration can be legitimate. This does not cover every script host, in-process execution, or non-Windows branch.

Windows process candidates. Sigma uses normalized process_creation fields; KQL requires Defender for Endpoint; SPL requires the Sysmon XML sourcetype. Tune collectors, fields and baselines before use.

Sigma
Draft SigmaDownload Sigma
title: Hunt - Suspicious Windows script execution
id: 2bb88802-9f03-4d99-a192-fe44c9484e8b
status: experimental
description: A script host or shell runs encoded content, a remote URL, or
  inline script syntax, then downloads or launches a payload.
author: MagicSword OpenAttacks catalog
date: 2026-10-23
falsepositives:
  - Authorized activity matching this broad hunt; baseline and investigate
    before alerting.
level: low
logsource:
  category: process_creation
  product: windows
detection:
  selection:
    Image|endswith:
      - \powershell.exe
      - \pwsh.exe
      - \mshta.exe
      - \wscript.exe
      - \cscript.exe
    CommandLine|contains:
      - -enc
      - http
      - FromBase64String
      - "javascript:"
      - "vbscript:"
  condition: selection
KQL
Draft KQLDownload KQL
// Draft hunt; requires Defender for Endpoint process telemetry for this OS.
DeviceProcessEvents
| where Timestamp > ago(7d)
| where FileName in~ ("powershell.exe", "pwsh.exe", "mshta.exe", "wscript.exe", "cscript.exe")
| where ProcessCommandLine contains "-enc" or ProcessCommandLine contains "http" or ProcessCommandLine contains "FromBase64String" or ProcessCommandLine contains "javascript:" or ProcessCommandLine contains "vbscript:"
| project Timestamp, DeviceName, AccountName, FileName, ProcessCommandLine, InitiatingProcessFileName, InitiatingProcessCommandLine, SHA1
| order by Timestamp desc
SPL
Draft SPLDownload SPL
sourcetype="XmlWinEventLog:Microsoft-Windows-Sysmon/Operational" EventCode=1
Image IN ("*\\powershell.exe", "*\\pwsh.exe", "*\\mshta.exe", "*\\wscript.exe", "*\\cscript.exe")
CommandLine IN ("*-enc*", "*http*", "*FromBase64String*", "*javascript:*", "*vbscript:*")
| table _time host User Image CommandLine ParentImage ParentCommandLine
| sort - _time
Investigation steps
  1. Follow the parent and child process tree and recover the script or URL from logs without executing it.
  2. Correlate the payload's signer/hash, persistence, and network activity; baseline approved automation.
Technical detailsTooling, impact

Attack context

AI's role
Agent / MCP as target
Initial access
Connect mcp-remote client to untrusted/compromised remote MCP server

Tooling as reported

AI products, models and artifacts

Other tooling

  • open()/PowerShell sink class

Targets and reported impact

Reported scale / exposure
CVSS 9.6 Critical

Detection rules

  • Review attack-specific indicatorsGUIDANCE

    Monitor for the techniques described in CVE-2025-6514 mcp-remote OAuth authorization_endpoint RCE. Refer to sources for specific IOCs and TTPs.

Source defensive notes

Upgrade mcp-remote ≥0.1.16; argv not shell for URLs; trust only pinned MCP origins

Sources & research credit

3 sources

Research by Or Peles / JFrog · JFrog

  1. jfrog.com
  2. github.com
  3. nvd.nist.gov
Record & downloads
Source record name
CVE-2025-6514 mcp-remote OAuth authorization_endpoint RCE
Entry ID
cve-2025-6514-mcp-remote-rce
Catalog review
October 20, 2026
Category
attacks-on-ai
AI involvement confidence
confirmed