Query Details

Copilot Studio Multi Stage Attack Chain

Query

id: a1b2c3d4-1013-4a11-9c01-0123456789b3
name: Copilot Studio - Multi-stage attack chain in a single conversation
description: |
  High-fidelity correlator. Raises an incident when one Copilot Studio
  conversation exhibits two or more distinct attack-stage signals -
  prompt injection, authority / role-impersonation, bulk-exfiltration
  intent, or jailbreak framing - optionally alongside connector / action
  execution in the same conversation. A realistic attack chain stacks
  these stages (inject -> escalate -> exfiltrate -> execute), so a
  conversation hitting several at once is far more likely to be a genuine
  attack than any single marker on its own.

  Aggregates inbound turns from AppEvents (Name == "BotMessageReceived")
  per conversationId and joins connector activity from AppDependencies.
  The text signals require "Log sensitive properties" on the agent's
  Application Insights settings; the connector-execution count works from
  metadata alone.
severity: High
requiredDataConnectors:
- connectorId: ApplicationInsights
  dataTypes:
  - AppEvents
  - AppDependencies
queryFrequency: PT1H
queryPeriod: PT1H
triggerOperator: gt
triggerThreshold: 0
enabled: true
tactics:
- InitialAccess
- PrivilegeEscalation
- Exfiltration
relevantTechniques:
- T1566
- T1078
- T1567
query: |
  let injectionMarkers = dynamic([
      "ignore previous instructions", "ignore all previous", "disregard previous",
      "you are now", "act as", "developer mode", "do anything now", "dan mode",
      "reveal your system prompt", "show your system prompt", "bypass your rules",
      "without any restrictions", "pretend you are", "from now on you"
  ]);
  let escalationMarkers = dynamic([
      "i am the ceo", "i am the cfo", "as an administrator", "as the administrator",
      "as an admin", "i have admin", "i am authorised", "i am authorized",
      "i have permission to", "on behalf of the", "grant me access", "elevate my access"
  ]);
  let exfilMarkers = dynamic([
      "show all", "list all", "list every", "export all", "give me every",
      "give me the full list", "all records", "all customers", "every user",
      "dump the", "entire database", "entire table", "select *"
  ]);
  let jailbreakMarkers = dynamic([
      "developer mode", "do anything now", "dan mode", "ignore your safety",
      "without restrictions", "bypass your rules", "disable your guardrails",
      "unrestricted mode", "you have no rules"
  ]);
  let conns =
      AppDependencies
      | where AppRoleName == "Microsoft Copilot Studio" or DependencyType == "Connector"
      | extend ConvId = tostring(Properties["conversationId"])
      | summarize ConnectorCalls = count(), Connectors = make_set(Name, 20),
                  ConnectorFailures = countif(Success == false) by ConvId;
  AppEvents
  | where Name == "BotMessageReceived"
  | extend
      ConvId = tostring(Properties["conversationId"]),
      Text   = tolower(tostring(Properties["text"]))
  | where isnotempty(Text)
  | extend
      SigInjection  = Text has_any (injectionMarkers),
      SigEscalation = Text has_any (escalationMarkers),
      SigExfil      = Text has_any (exfilMarkers),
      SigJailbreak  = Text has_any (jailbreakMarkers)
  | summarize
      Injection  = countif(SigInjection) > 0,
      Escalation = countif(SigEscalation) > 0,
      Exfil      = countif(SigExfil) > 0,
      Jailbreak  = countif(SigJailbreak) > 0,
      Messages   = count(),
      FirstSeen  = min(TimeGenerated),
      LastSeen   = max(TimeGenerated),
      UserId     = take_any(UserId),
      ChannelId  = take_any(tostring(Properties["channelId"])),
      ClientIP   = take_any(ClientIP),
      SampleText = make_set(substring(tostring(Properties["text"]), 0, 200), 5)
      by ConvId
  | extend Stages = toint(Injection) + toint(Escalation) + toint(Exfil) + toint(Jailbreak)
  | where Stages >= 2
  | join kind=leftouter conns on ConvId
  | extend
      AccountName    = iff(isempty(UserId), "unknown-agent", UserId),
      ConnectorCalls = coalesce(ConnectorCalls, 0),
      TimeGenerated  = LastSeen
  | project
      TimeGenerated, FirstSeen, LastSeen, AccountName, ConvId, ChannelId, ClientIP,
      Stages, Injection, Escalation, Exfil, Jailbreak,
      Messages, ConnectorCalls, ConnectorFailures, Connectors, SampleText
  | order by Stages desc, LastSeen desc
entityMappings:
- entityType: Account
  fieldMappings:
  - identifier: Name
    columnName: AccountName
- entityType: IP
  fieldMappings:
  - identifier: Address
    columnName: ClientIP
eventGroupingSettings:
  aggregationKind: SingleAlert
incidentConfiguration:
  createIncident: true
  groupingConfiguration:
    enabled: true
    reopenClosedIncident: false
    lookbackDuration: PT6H
    matchingMethod: Selected
    groupByEntities:
    - Account
    groupByAlertDetails: []
    groupByCustomDetails: []
version: 1.0.0
kind: Scheduled
tags:
- Sentinel-As-Code
- Custom
- CopilotStudio
- AI
- MultiStage
- AttackChain

Explanation

This query is designed to detect potential multi-stage attack attempts within conversations in Microsoft Copilot Studio. It monitors conversations for specific suspicious activities, such as:

  1. Prompt Injection: Attempts to manipulate the system by inserting commands like "ignore previous instructions" or "bypass your rules."
  2. Authority/Role Impersonation: Phrases suggesting unauthorized access, like "i am the ceo" or "grant me access."
  3. Bulk Exfiltration Intent: Requests for large amounts of data, such as "show all" or "entire database."
  4. Jailbreak Framing: Attempts to disable security measures, using terms like "developer mode" or "unrestricted mode."

The query aggregates messages from conversations and checks for these markers. If a conversation contains two or more of these suspicious signals, it is flagged as a potential attack. The query also considers connector activity within the same conversation to enhance detection accuracy.

The query runs every hour and generates an alert if any conversation meets the criteria. It creates an incident for further investigation, grouping alerts by account and considering recent activity within a six-hour window. The goal is to identify genuine threats by detecting multiple attack stages occurring together, rather than isolated suspicious actions.

Details

David Alonso profile picture

David Alonso

Released: June 8, 2026

Tables

AppDependenciesAppEvents

Keywords

CopilotStudioApplicationInsightsAppEventsAppDependenciesAccountIPUserChannelClientIPConnectorConnectorsMessagesStagesInjectionEscalationExfilJailbreakTimeGenerated

Operators

letdynamicorextendtostringsummarizecountmake_setcountifwhereisnotemptytolowerhas_anyminmaxtake_anysubstringbytointjoinkindleftouteriffisemptycoalesceprojectorder bydesc

Actions