# GhostAction Stage 2 stealer (AI credential theft)

- ID: ghostaction-ai-creds-2026-10
- Reported: 2026-10-16
- Researcher: Thijs Xhaflaire (Jamf Threat Labs); OpenSourceMalware deep dive
- Organization: Jamf Threat Labs / OpenSourceMalware
- AI role: ai_credential_theft (AI credential theft)
- Confidence in AI involvement: not assessed
- Research / borderline: true
- Last reviewed: 2026-10-20
- Entry page: https://openattacks.ai/attacks/ghostaction-ai-creds-2026-10/
- Entry JSON: https://openattacks.ai/api/attacks/ghostaction-ai-creds-2026-10.json
- Browse title: GhostAction Stage 2 stealer targeting cloud and AI credentials
- Editorial summary: Malicious workflows and a VS Code auto-run task steal AWS, npm, SSH and Claude/Gemini credentials across 94 repos. AI is a credential target here, not the attack operator.
- Evidence class (catalog annotation): Reported campaign
- Source-stated target environments: Developer workflows; Cloud & SaaS
- Stage hunts and conditional defenses: https://openattacks.ai/api/defenses/ghostaction-ai-creds-2026-10.json

## Evidence qualification
Primary attack is CI secret theft + VS Code folderOpen stealer; AI is a credential target (Claude/Gemini keys), not the attack operator. Included because Jose's post calls out AI tooling theft.

## Technique
GhostAction pushes malicious GitHub Actions then Stage 2: .vscode/tasks.json folderOpen runs node on fake fa-solid-400.woff2 JS stealer; cron \*/5 pulls C2. Targets AWS/npm/git/kube/SSH plus Claude/Gemini creds. 94 repos / 66 owners. PolinRider copycat technique, not DPRK per OSM.

## Stack relevance (editorial)
Assessment: mapped. Editorial applicability reviewed against the catalog source account; not a scan or independent incident verification.
First action: Review workflow and folder-open task changes, then rotate exposed development and AI credentials.
- Relationship: credential; tools: claude-code, claude, gemini, ai-api-keys, npm-pypi; OS scope: not OS-specific / not stated; requires existing MCP connections: false.
  Relevance: The reported stealer targets local development, cloud and Claude / Gemini credentials.
  Condition to check: The malicious workflow or VS Code folder-open task must run with access to locally stored credentials.
  Condition to check: AI is a credential target in this account; the report does not establish an AI-operated intrusion.
  Evidence: https://opensourcemalware.com/blog/ghostaction-copycats-polinrider-by-hiding-a-stealer-in-a-fake-font-file
A product mention alone is not a victim-side applicability mapping. Selection does not verify affected versions, permissions or compromise.

## Initial access
Compromised GitHub account → malicious workflow + VS Code trusted workspace auto task

## AI tooling and models
- Targets [Claude](https://claude.com/product/overview) and [Gemini](https://gemini.google.com/) credential stores

## Other tooling
- [GitHub Actions](https://github.com/features/actions)
- [VS Code](https://github.com/microsoft/vscode) tasks.json
- [node](https://github.com/nodejs/node)
- cron
- 193.32.204.199:8080

## Victims and sectors
GitHub maintainers / developers (many dormant repos)

## Target geography
- unknown

## Attribution
GhostAction; PolinRider-technique copycat (no shared IOCs with DPRK per OSM)

## Scale and metrics
94 compromised repos; Stage 1 Oct 8, Stage 2 Oct 15 2026

## Attack flow
Catalog reconstruction of the supplied source account. Unknowns and research caveats are preserved.
### step-1: Compromised account changes a repository [access]
Malicious GitHub Actions and workspace tasks are introduced.
Evidence: https://opensourcemalware.com/blog/ghostaction-copycats-polinrider-by-hiding-a-stealer-in-a-fake-font-file

### step-2: Trusted workspace opens a task [execution]
VS Code executes Node content disguised as a font file.
Evidence: https://opensourcemalware.com/blog/ghostaction-copycats-polinrider-by-hiding-a-stealer-in-a-fake-font-file

### step-3: AI credential stores are searched [ai]
The stealer targets Claude and Gemini tokens alongside cloud and developer credentials.
Evidence: https://opensourcemalware.com/blog/ghostaction-copycats-polinrider-by-hiding-a-stealer-in-a-fake-font-file

### step-4: Secrets are stolen with persistence [impact]
The report describes periodic C2 retrieval through cron and a multi-repository campaign.
Evidence: https://opensourcemalware.com/blog/ghostaction-copycats-polinrider-by-hiding-a-stealer-in-a-fake-font-file

Connections:
- step-1 -> step-2
- step-2 -> step-3
- step-3 -> step-4

## 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.
### step-1: 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.
- No direct MagicSword prevention claim is recorded for this stage.

### step-2: Agent trust / configuration changes
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/mcp-config.sigma.yml
- KQL query download: /api/detections/mcp-config.kql
- SPL query download: /api/detections/mcp-config.spl
- Hunt hypothesis: A repository, dependency or agent changes MCP commands, automatic-task settings, tool approval or model-routing configuration before new execution.
- Required telemetry: File changes and before/after content for MCP / IDE configuration; Repository audit / pull-request history; Agent startup and tool-invocation logs
- Investigate: Diff command, args, environment, origin, autoApprove and task settings against the previously approved version.
- Investigate: Correlate the author and change with the next agent launch; inspect path canonicalization and trailing-dot variants where relevant.
- Limitation: A file-write event alone cannot establish what changed. Legitimate setup also changes these files; obtain a diff and authorization context.
- No direct MagicSword prevention claim is recorded for this stage.

### step-3: 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.

### step-4: New persistence → recurring execution
- Visibility: Defender-side logs where collected
- Query origin: catalog_authored; status: draft; log scope: custom_schema
- SIGMA query download: /api/detections/persistence.sigma.yml
- KQL query download: /api/detections/persistence.kql
- SPL query download: /api/detections/persistence.spl
- Hunt hypothesis: A task, Run key, cron entry, shell profile, or startup file is changed and later launches the same unexpected program.
- Required telemetry: Platform-specific registry, scheduled-task, cron and startup-file changes; Process creation and file provenance; User / administrative change records
- Investigate: Diff the persistence artifact and identify the creating process / principal.
- Investigate: Correlate the subsequent launch and network behavior; baseline deployment and management agents.
- Limitation: Windows and Unix persistence require different collectors. A configuration change without a subsequent launch is not proof that persistence ran.
- 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.T0055: Unsecured Credentials — The stealer searches local AI credential stores.
  Technique: https://atlas.mitre.org/techniques/AML.T0055
  Evidence: https://opensourcemalware.com/blog/ghostaction-copycats-polinrider-by-hiding-a-stealer-in-a-fake-font-file

## Defensive notes
task.allowAutomaticTasks off; Restricted Mode; crontab -l for \#ghc2; rotate Claude/Gemini/cloud/git creds

## Sources
- https://opensourcemalware.com/blog/ghostaction-copycats-polinrider-by-hiding-a-stealer-in-a-fake-font-file
