Detection queries Provider reportProvider-side

Claude-orchestrated influence-as-a-service bot network

A provider report describes an operation using Claude to coordinate over 100 social bot accounts and generate responses. The source does not confirm state affiliation.

What happened

Financially motivated influence-as-a-service used Claude not only for content but to decide when 100+ social bot accounts should like, share, comment, or ignore posts based on client political personas. Also generated multilingual responses and image-gen prompts.

Read the original source

How it happened

Select a stage to explore its defenses
Detect this stage
Detect this stage
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 · Operator defines political personas

    Commercial clients supply narratives and personas for social accounts.

    Hunt: A model-provider investigation correlates related accounts, repeated offensive requests and shared infrastructure or exposed operator sessions.

    Attacker-side planning is generally absent from victim SIEM logs. These templates require provider-owned audit data and do not identify AI use from a victim process alone.

    Source for step 1
  2. 02 · Claude plans account activity

    Claude helps decide when more than 100 bot accounts should engage or ignore posts.

    Hunt: A model-provider investigation correlates related accounts, repeated offensive requests and shared infrastructure or exposed operator sessions.

    Attacker-side planning is generally absent from victim SIEM logs. These templates require provider-owned audit data and do not identify AI use from a victim process alone.

    Source for step 2
  3. 03 · Accounts distribute content

    The operation uses multilingual responses and generated image prompts.

    Hunt: Related accounts or assistants repeat correlated posting, forwarding or tool actions beyond the expected user workflow.

    Requires platform-side visibility. Similar content and synchronized activity can have legitimate explanations.

    Source for step 3
  4. 04 · Coordinated influence

    Authentic social accounts encounter the coordinated engagement; state affiliation is unconfirmed.

    Hunt: Related accounts or assistants repeat correlated posting, forwarding or tool actions beyond the expected user workflow.

    Requires platform-side visibility. Similar content and synchronized activity can have legitimate explanations.

    Source for step 4

Why it matters

Reported entry point: n/a (influence ops on social platforms). Reported impact: Authentic social accounts encounter the coordinated engagement; state affiliation is unconfirmed; reported targets include Tens of thousands of authentic social accounts engaged; clients outside US with varied political narratives; state-affiliated style not confirmed; using the named AI products does not by itself establish exposure.

Read the original report

What you can do

Protection & prevention

Platform bot detection; model-provider abuse monitoring (Anthropic banned accounts)

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

Review the original guidance
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.

01Operator defines political personasProvider-side abuse investigationCustom schema · Draft

Commercial clients supply narratives and personas for social accounts.

What to look for

A model-provider investigation correlates related accounts, repeated offensive requests and shared infrastructure or exposed operator sessions.

Persona preparation is visible in provider/operator records, rather than victim endpoint logs.

Visibility: Provider / operator records

Required logs

  • Provider-owned account / request audit
  • Abuse-review findings and linked-account context
  • Lawfully available exposed operator-session evidence

Coverage limit. Attacker-side planning is generally absent from victim SIEM logs. These templates require provider-owned audit data and do not identify AI use from a victim process alone.

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 - Provider-side abuse investigation
id: c8c1edc0-c79a-4644-a876-2c1a6cb9a438
status: experimental
description: A model-provider investigation correlates related accounts,
  repeated offensive requests and shared infrastructure or exposed operator
  sessions.
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:
      - model.request
  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 ("model.request")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated desc
SPL
Draft SPLDownload SPL
sourcetype="openattacks:audit"
EventType IN ("model.request")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _time
Investigation steps
  1. Correlate accounts, request rates, infrastructure and source-described behavior in provider-owned records.
  2. For victim-side defense, pivot to the reported execution or access stage rather than trying to detect attacker-side prompts.
02Claude plans account activityProvider-side abuse investigationCustom schema · Draft

Claude helps decide when more than 100 bot accounts should engage or ignore posts.

What to look for

A model-provider investigation correlates related accounts, repeated offensive requests and shared infrastructure or exposed operator sessions.

Visibility: Provider / operator records

Required logs

  • Provider-owned account / request audit
  • Abuse-review findings and linked-account context
  • Lawfully available exposed operator-session evidence

Coverage limit. Attacker-side planning is generally absent from victim SIEM logs. These templates require provider-owned audit data and do not identify AI use from a victim process alone.

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 - Provider-side abuse investigation
id: c8c1edc0-c79a-4644-a876-2c1a6cb9a438
status: experimental
description: A model-provider investigation correlates related accounts,
  repeated offensive requests and shared infrastructure or exposed operator
  sessions.
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:
      - model.request
  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 ("model.request")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated desc
SPL
Draft SPLDownload SPL
sourcetype="openattacks:audit"
EventType IN ("model.request")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _time
Investigation steps
  1. Correlate accounts, request rates, infrastructure and source-described behavior in provider-owned records.
  2. For victim-side defense, pivot to the reported execution or access stage rather than trying to detect attacker-side prompts.
03Accounts distribute contentCoordinated messaging / propagationCustom schema · Draft

The operation uses multilingual responses and generated image prompts.

What to look for

Related accounts or assistants repeat correlated posting, forwarding or tool actions beyond the expected user workflow.

Visibility: Platform / application records

Required logs

  • Platform account and posting audit
  • Agent session and message-provenance records
  • Rate, recipient and content-similarity features

Coverage limit. Requires platform-side visibility. Similar content and synchronized activity can have legitimate explanations.

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 - Coordinated messaging / propagation
id: c4001568-b68b-4887-a86f-6f05807640f6
status: experimental
description: Related accounts or assistants repeat correlated posting,
  forwarding or tool actions beyond the expected user workflow.
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:
      - social.post
      - message.forward
  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 ("social.post", "message.forward")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated desc
SPL
Draft SPLDownload SPL
sourcetype="openattacks:audit"
EventType IN ("social.post", "message.forward")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _time
Investigation steps
  1. Group actions by linked account, session, recipient and time rather than judging writing style.
  2. Compare propagation with legitimate campaigns and preserve whether the source describes a lab demonstration or observed abuse.
04Coordinated influenceCoordinated messaging / propagationCustom schema · Draft

Authentic social accounts encounter the coordinated engagement; state affiliation is unconfirmed.

What to look for

Related accounts or assistants repeat correlated posting, forwarding or tool actions beyond the expected user workflow.

Review linked posting and engagement on the platform; coordinated activity does not establish state affiliation.

Visibility: Platform / application records

Required logs

  • Platform account and posting audit
  • Agent session and message-provenance records
  • Rate, recipient and content-similarity features

Coverage limit. Requires platform-side visibility. Similar content and synchronized activity can have legitimate explanations.

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 - Coordinated messaging / propagation
id: c4001568-b68b-4887-a86f-6f05807640f6
status: experimental
description: Related accounts or assistants repeat correlated posting,
  forwarding or tool actions beyond the expected user workflow.
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:
      - social.post
      - message.forward
  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 ("social.post", "message.forward")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated desc
SPL
Draft SPLDownload SPL
sourcetype="openattacks:audit"
EventType IN ("social.post", "message.forward")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _time
Investigation steps
  1. Group actions by linked account, session, recipient and time rather than judging writing style.
  2. Compare propagation with legitimate campaigns and preserve whether the source describes a lab demonstration or observed abuse.
Technical detailsTooling, impact & MITRE ATLAS

Attack context

AI's role
AI as operator
Initial access
n/a (influence ops on social platforms)

Tooling as reported

AI products, models and artifacts

  • Claude
  • image-generation tools (prompts only)

Targets and reported impact

Targets / sectors
Tens of thousands of authentic social accounts engaged; clients outside US with varied political narratives; state-affiliated style not confirmed
Reported scale / exposure
100+ bot accounts on X/Facebook; tens of thousands of engagements; no viral hits noted
Target geography
Multiple regions

The source identifies clients in multiple countries outside the United States; individual target countries are not disclosed.

Reported attribution

unknown commercially motivated operator; state affiliation not confirmed

Structured attribution

Actor
unknown commercially motivated operator

Detection rules

  • Review attack-specific indicatorsGUIDANCE

    Monitor for the techniques described in Claude-orchestrated influence-as-a-service bot network. Refer to sources for specific IOCs and TTPs.

Source defensive notes

Platform bot detection; model-provider abuse monitoring (Anthropic banned accounts)

MITRE ATLAS

AI-specific catalog annotations based on the reported behavior; these are not MITRE case-study assignments.

AML.T0016.002Generative AI

The supplied source explicitly describes generative-model tooling assisting the reported activity; this mapping does not establish additional autonomy or victim impact. Source

Sources & research credit

1 source

Research by Anthropic Threat Intelligence · Anthropic

  1. anthropic.com
Record & downloads
Source record name
Claude-orchestrated influence-as-a-service bot network
Entry ID
anthropic-influence-as-a-service-2025-03
Catalog review
October 20, 2026
Category
adversary-use-of-ai
AI involvement confidence
confirmed