hackerbot-claw autonomous GitHub Actions exploitation
Mar 1, 2026: StepSecurity discovered hackerbot-claw, autonomous agent exploiting misconfigured GitHub Actions workflows. Agent scans public repositories for insecure workflow patterns (untrusted input…
What happened
Mar 1, 2026: StepSecurity discovered hackerbot-claw, autonomous agent exploiting misconfigured GitHub Actions workflows. Agent scans public repositories for insecure workflow patterns (untrusted input injection, secrets exposure, pull_request_target misuse), automatically submits exploits, harvests exposed secrets and GITHUB_TOKEN, pivots to other repositories accessible with stolen credentials. Fully autonomous: scans, exploits, collects, pivots without operator intervention. Attribution unknown.
hackerbot-claw autonomous agent exploits misconfigured GitHub Actions workflows
How it happened
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.
- 01 · Scan public repositories
Agent scans for insecure GitHub Actions patterns
Source for step 1 - 02 · Submit automated exploits
Submit pull requests or trigger workflows to exploit untrusted input injection, secrets exposure
Hunt: A package or workflow change introduces a lifecycle hook, remote dependency or new command that accesses secrets or external services.
Package installation and unfamiliar names are not malicious by themselves. Dependency resolution and CI audit records are required.
Source for step 2 - 03 · Harvest secrets and tokens
Collect exposed secrets, GITHUB_TOKEN credentials
Hunt: An unexpected process or tool accesses credential stores and is followed by token use or outbound transfer inconsistent with the owner.
Defender DeviceFileEvents is not a general file-read audit trail. Collect suitable object-access, EDR or application logs; legitimate developer tools also read secrets.
Source for step 3 - 04 · Pivot to accessible repositories
Use stolen credentials to access and compromise additional repositories
Hunt: A token or agent reads private material and creates a public issue, repository, commit or visibility change inconsistent with the approved task.
Git-provider audit completeness depends on product and plan. Not every file read or issue body is present in organization audit logs.
Source for step 4
Why it matters
Reported entry point: Public GitHub scanning. Reported impact: Collect exposed secrets, GITHUB_TOKEN credentials; reported targets include Open-source projects with insecure GitHub Actions workflows; applicability to your setup has not been assessed, so verify affected versions, permissions, and configuration in the original report.
What you can do
Protection & prevention
Secure GitHub Actions workflows; avoid untrusted input in run commands; use StepSecurity Harden Runner; rotate exposed secrets; restrict workflow permissions
Catalog defensive guidance based on the reported behavior. Confirm scope and current mitigations in the original source.
Detection queries
Draft query starters grouped by the attack stages where they apply.
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.
02Submit automated exploitsDependency / CI trust boundaryCustom schema · Draft
Submit pull requests or trigger workflows to exploit untrusted input injection, secrets exposure
What to look for
A package or workflow change introduces a lifecycle hook, remote dependency or new command that accesses secrets or external services.
Review workflow changes and runs involving untrusted pull-request input; a submitted pull request is not proof of execution.
Visibility: Defender-side logs where collected
Required logs
- Package-manager and CI job logs
- Lockfile / manifest / workflow diffs
- Runner process trees, secret access and egress
Coverage limit. Package installation and unfamiliar names are not malicious by themselves. Dependency resolution and CI audit records are required.
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
title: Hunt - Dependency / CI trust boundary
id: 5fa9c45a-ac1c-4666-a598-e80626320997
status: experimental
description: A package or workflow change introduces a lifecycle hook, remote
dependency or new command that accesses secrets or external services.
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:
- package.install
- ci.workflow.change
- package.lifecycle.exec
condition: selection
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 ("package.install", "ci.workflow.change", "package.lifecycle.exec")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated descSPL
sourcetype="openattacks:audit"
EventType IN ("package.install", "ci.workflow.change", "package.lifecycle.exec")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _timeInvestigation steps
- Compare package provenance, publish identity, lifecycle scripts and resolved dependency URLs with the approved version.
- Correlate the install or workflow to secret reads and subsequent token use; distinguish exposure from confirmed compromise.
03Harvest secrets and tokensSensitive store access → credential useCustom schema · Draft
Collect exposed secrets, GITHUB_TOKEN credentials
What to look for
An unexpected process or tool accesses credential stores and is followed by token use or outbound transfer inconsistent with the owner.
Visibility: Defender-side logs where collected
Required logs
- File-read / API access telemetry for relevant secret stores
- Process identity and command lines
- Identity, token and outbound-network audit logs
Coverage limit. Defender DeviceFileEvents is not a general file-read audit trail. Collect suitable object-access, EDR or application logs; legitimate developer tools also read secrets.
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
title: Hunt - Sensitive store access → credential use
id: 46c46c62-2d83-4198-a8bf-d6637094527b
status: experimental
description: An unexpected process or tool accesses credential stores and is
followed by token use or outbound transfer inconsistent with the owner.
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:
- secret.read
- credential.store.read
condition: selection
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 ("secret.read", "credential.store.read")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated descSPL
sourcetype="openattacks:audit"
EventType IN ("secret.read", "credential.store.read")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _timeInvestigation steps
- Identify the actor, process and exact store touched, then pivot to token use from new devices or infrastructure.
- Correlate reads with egress and rotate affected credentials after confirming exposure.
04Pivot to accessible repositoriesPrivate access → public repository artifactCustom schema · Draft
Use stolen credentials to access and compromise additional repositories
What to look for
A token or agent reads private material and creates a public issue, repository, commit or visibility change inconsistent with the approved task.
Visibility: Defender-side logs where collected
Required logs
- Git-provider organization / enterprise audit
- Repository and token permission inventory
- Agent tool and secret-scanning / DLP records
Coverage limit. Git-provider audit completeness depends on product and plan. Not every file read or issue body is present in organization audit logs.
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
title: Hunt - Private access → public repository artifact
id: b7b2d3f0-8170-4225-accb-c20633364ef4
status: experimental
description: A token or agent reads private material and creates a public issue,
repository, commit or visibility change inconsistent with the approved 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:
- repository.public.write
- repository.visibility.change
condition: selection
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 ("repository.public.write", "repository.visibility.change")
| project TimeGenerated, EventType, Actor, Asset, Action, Target, CorrelationId
| order by TimeGenerated descSPL
sourcetype="openattacks:audit"
EventType IN ("repository.public.write", "repository.visibility.change")
| table _time EventType Actor Asset Action Target CorrelationId
| sort - _timeInvestigation steps
- Join access and public-write actions by actor / token and time; inspect visibility changes and newly created repositories.
- Verify whether the artifact contains sensitive data using approved scanning, retaining original source qualifications.
Technical detailsTooling, impact & MITRE ATLAS
Attack context
- AI's role
- AI as operator
- Initial access
- Public GitHub scanning
Tooling as reported
AI products, models and artifacts
- Autonomous agent (model/framework unspecified)
Other tooling
- GitHub Actions exploitation
- Automated secret harvesting
Targets and reported impact
- Targets / sectors
- Open-source projects with insecure GitHub Actions workflows
- Reported scale / exposure
- Hundreds of repositories scanned and exploited; multiple secrets stolen as of Mar 2026
- Target geography
- Multiple regions
Reported attribution
Unknown actor
Structured attribution
- Actor
- Unknown
- Country
- Unknown
- Motivation
- unknown
- Attributed by
- StepSecurity
- Attribution confidence
- low
Detection rules
- GitHub Self-Hosted Runner Suspicious ExecutionSIGMAView rule
Detects suspicious execution from GitHub self-hosted runners; relevant for hackerbot-claw exploiting GitHub Actions
- GitHub Actions Workflow Modification BlockedELASTICView rule
Detects GitHub Actions workflow injection attempts; directly applicable to hackerbot-claw exploitation
- GitHub Actions exploitation monitoringGUIDANCE
Monitor for automated pull requests with suspicious workflow triggers; alert on unexpected secret access or GITHUB_TOKEN usage; detect rapid workflow execution spikes
Activity timeline
- First seen
- 2026-03-01
- Last updated
- 2026-11-05
Updates
- 2026-03-01 — StepSecurity
hackerbot-claw autonomous GitHub Actions exploitation disclosed
Source defensive notes
Secure GitHub Actions workflows; avoid untrusted input in run commands; use StepSecurity Harden Runner; rotate exposed secrets; restrict workflow permissions
MITRE ATLAS
AI-specific catalog annotations based on the reported behavior; these are not MITRE case-study assignments.
Autonomous agent exploits GitHub Actions workflows to harvest secrets and pivot Source
Sources & research credit
1 sourceResearch by StepSecurity · StepSecurity
StepSecurity analysis. Detection: monitor for automated pull requests exploiting workflow patterns, mass secret access, rapid workflow execution spikes from untrusted actors.
Record & downloads
- Source record name
- hackerbot-claw autonomous GitHub Actions exploitation
- Entry ID
- hackerbot-claw-github-actions-2026-03
- Catalog review
- November 5, 2026
- Category
- adversary-use-of-ai
- AI involvement confidence
- confirmed