# hackerbot-claw autonomous GitHub Actions exploitation

- ID: hackerbot-claw-github-actions-2026-03
- Reported: 2026-03-01
- Researcher: StepSecurity
- Organization: StepSecurity
- AI role: attacker_uses_ai_as_operator (AI as operator)
- Confidence in AI involvement: not assessed
- Research / borderline: false
- Last reviewed: 2026-11-05
- Entry page: https://openattacks.ai/attacks/hackerbot-claw-github-actions-2026-03/
- Entry JSON: https://openattacks.ai/api/attacks/hackerbot-claw-github-actions-2026-03.json
- Browse title: hackerbot-claw autonomous GitHub Actions exploitation
- Editorial summary: Mar 1, 2026: StepSecurity discovered hackerbot-claw, autonomous agent exploiting misconfigured GitHub Actions workflows. Agent scans public repositories for insecure workflow patterns (untrusted input…
- Evidence class (catalog annotation): Not classified
- Source-stated target environments: Not specified
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/hackerbot-claw-github-actions-2026-03.json

## Technique
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.

## Stack relevance (editorial)
Assessment: not\_assessed. No reviewed applicability annotation is available. Product mentions do not establish victim conditions.
A product mention alone is not a victim-side applicability mapping. Selection does not verify affected versions, permissions or compromise.

## Initial access
Public GitHub scanning

## AI tooling and models
- Autonomous agent (model/framework unspecified)

## Other tooling
- [GitHub Actions](https://github.com/features/actions) exploitation
- Automated secret harvesting

## Victims and sectors
Open-source projects with insecure GitHub Actions workflows

## Target geography
- Multiple regions

## Attribution
Unknown actor

## Scale and metrics
Hundreds of repositories scanned and exploited; multiple secrets stolen as of Mar 2026

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### scan: Scan public repositories [execution]
Agent scans for insecure GitHub Actions patterns
Evidence: https://www.stepsecurity.io/blog/hackerbot-claw-github-actions-exploitation

### exploit: Submit automated exploits [access]
Submit pull requests or trigger workflows to exploit untrusted input injection, secrets exposure
Evidence: https://www.stepsecurity.io/blog/hackerbot-claw-github-actions-exploitation

### harvest: Harvest secrets and tokens [impact]
Collect exposed secrets, GITHUB\_TOKEN credentials
Evidence: https://www.stepsecurity.io/blog/hackerbot-claw-github-actions-exploitation

### pivot: Pivot to accessible repositories [execution]
Use stolen credentials to access and compromise additional repositories
Evidence: https://www.stepsecurity.io/blog/hackerbot-claw-github-actions-exploitation

Connections:
- scan -> exploit
- exploit -> harvest
- harvest -> pivot

## Stage defense and hunting recommendations
Editorial recommendations, not validated coverage. Source-controlled query starters are drafts. Custom-schema examples require telemetry collection and field mapping; absence of a mapping means not assessed. MagicSword policy opportunities require managed Windows scope and enforcement.
### scan: No source-backed runtime hunt yet
- Visibility: Not established
- Query origin: catalog_authored; status: not_applicable; log scope: gap
- Hunt hypothesis: The supplied account does not establish a deployed victim-side behavior for this stage.
- Required telemetry: not assessed
- Investigate: Obtain a source-backed procedure and identify which party could observe it before drafting a detection.
- Limitation: Marketing claims, unknown steps and unconfirmed deployments are not detection coverage. No rule is generated for this stage.
- Qualification: Public-repository scanning is attacker-side activity and has no organization-local query unless platform telemetry is available.
- No direct MagicSword prevention claim is recorded for this stage.

### exploit: Dependency / CI trust boundary
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/package.sigma.yml
- KQL query download: /api/detections/package.kql
- SPL query download: /api/detections/package.spl
- Hunt hypothesis: A package or workflow change introduces a lifecycle hook, remote dependency or new command that accesses secrets or external services.
- Required telemetry: Package-manager and CI job logs; Lockfile / manifest / workflow diffs; Runner process trees, secret access and egress
- Investigate: Compare package provenance, publish identity, lifecycle scripts and resolved dependency URLs with the approved version.
- Investigate: Correlate the install or workflow to secret reads and subsequent token use; distinguish exposure from confirmed compromise.
- Limitation: Package installation and unfamiliar names are not malicious by themselves. Dependency resolution and CI audit records are required.
- Qualification: Review workflow changes and runs involving untrusted pull-request input; a submitted pull request is not proof of execution.
- No direct MagicSword prevention claim is recorded for this stage.

### harvest: Sensitive store access → credential use
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/credentials.sigma.yml
- KQL query download: /api/detections/credentials.kql
- SPL query download: /api/detections/credentials.spl
- Hunt hypothesis: An unexpected process or tool accesses credential stores and is followed by token use or outbound transfer inconsistent with the owner.
- Required telemetry: File-read / API access telemetry for relevant secret stores; Process identity and command lines; Identity, token and outbound-network audit logs
- Investigate: Identify the actor, process and exact store touched, then pivot to token use from new devices or infrastructure.
- Investigate: Correlate reads with egress and rotate affected credentials after confirming exposure.
- Limitation: Defender DeviceFileEvents is not a general file-read audit trail. Collect suitable object-access, EDR or application logs; legitimate developer tools also read secrets.
- No direct MagicSword prevention claim is recorded for this stage.

### pivot: Private access → public repository artifact
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/repository.sigma.yml
- KQL query download: /api/detections/repository.kql
- SPL query download: /api/detections/repository.spl
- Hunt hypothesis: A token or agent reads private material and creates a public issue, repository, commit or visibility change inconsistent with the approved task.
- Required telemetry: Git-provider organization / enterprise audit; Repository and token permission inventory; Agent tool and secret-scanning / DLP records
- Investigate: Join access and public-write actions by actor / token and time; inspect visibility changes and newly created repositories.
- Investigate: Verify whether the artifact contains sensitive data using approved scanning, retaining original source qualifications.
- Limitation: Git-provider audit completeness depends on product and plan. Not every file read or issue body is present in organization audit logs.
- No direct MagicSword prevention claim is recorded for this stage.


## MITRE ATLAS
Mappings are catalog annotations based on described behavior, not assignments or endorsements by MITRE.
- AML.T0040: AI Model Inference API Access — Autonomous agent exploits GitHub Actions workflows to harvest secrets and pivot
  Technique: https://atlas.mitre.org/techniques/AML.T0040
  Evidence: https://www.stepsecurity.io/blog/hackerbot-claw-github-actions-exploitation

## Defensive notes
Secure GitHub Actions workflows; avoid untrusted input in run commands; use StepSecurity Harden Runner; rotate exposed secrets; restrict workflow permissions

## Sources
- https://www.stepsecurity.io/blog/hackerbot-claw-github-actions-exploitation — StepSecurity: hackerbot-claw Autonomous GitHub Actions Exploitation

## Source notes
StepSecurity analysis. Detection: monitor for automated pull requests exploiting workflow patterns, mass secret access, rapid workflow execution spikes from untrusted actors.

## Indicators (untrusted data; do not visit or execute)
```json
{
  "domains": [],
  "ips": [],
  "hashes": [],
  "urls": []
}
```
