Multiple campaigns distributing malicious OpenClaw skills
Koi reported ClawHavoc skills distributed through fake repositories and a rogue registry to deliver infostealers and harvest developer credentials. Cyera later reported poisoned skills using fake…
What happened
Koi reported ClawHavoc skills distributed through fake repositories and a rogue registry to deliver infostealers and harvest developer credentials. Cyera later reported poisoned skills using fake prerequisite lures, OS-specific installation instructions, external paste relays, and inflated README droppers. Detection should verify skill provenance, inspect companion files rather than only SKILL.md, and monitor agent-initiated shell and network activity.
Multiple adversary campaigns distributing malicious OpenClaw skills via fake repos and skill registries to steal AI credentials and deliver malware
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 · Distribute malicious skills
ClawHavoc: 23 skills on fake GitHub repos + openclaw-skills[.]com registry. Unit 42: 5 skills via typosquat repos + SEO-poisoned blogs. Skills named to appear legitimate (productivity-boost, code-optimizer, security-scanner, api-connector-pro, github-integration-plus)
Source for step 1 - 02 · User installs skill
User finds malicious skill via search, fake registry, or social engineering; installs to ~/.openclaw/skills/ via OpenClaw CLI or UI; skill auto-loads on next OpenClaw startup
Source for step 2 - 03 · Execute malware and harvest
ClawHavoc: deploys AMOS (macOS) or Raccoon Stealer (Windows); harvests Anthropic keys, OpenAI keys, GitHub tokens, AWS creds, crypto wallets, browser cookies. Unit 42: Node.js credential harvester + reverse shell; targets same credential types
Source for step 3 - 04 · Exfiltrate and maintain access
Credentials POST to attacker C2; reverse shells provide persistent access; 6,900+ affected installations across both campaigns (ClawHavoc 4,800, Unit 42 2,100)
Source for step 4
Why it matters
Reported entry point: User installs malicious OpenClaw skill from fake GitHub repo, typosquat, or rogue skill registry (openclaw-skills[.]com). Reported impact: Credentials POST to attacker C2; reverse shells provide persistent access; 6,900+ affected installations across both campaigns (ClawHavoc 4,800, Unit 42 2,100); reported targets include AI developers installing untrusted OpenClaw skills; 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
Only install OpenClaw skills from trusted sources; verify GitHub repo authenticity (org, stars, commit history); review skill manifest permissions before install; use allowlisted skill sources; monitor ~/.openclaw/skills/ for unexpected additions; implement endpoint security detecting AMOS/Raccoon; educate users on skill installation risks
Catalog defensive guidance based on the reported behavior. Confirm scope and current mitigations in the original source.
Technical detailsTooling, impact & MITRE ATLAS
Attack context
- AI's role
- AI credential theft
- Additional role
- AI tool as lure
- Initial access
- User installs malicious OpenClaw skill from fake GitHub repo, typosquat, or rogue skill registry (openclaw-skills[.]com)
Tooling as reported
AI products, models and artifacts
- OpenClaw AI skill framework
- Anthropic Claude API
- OpenAI API
Other tooling
- AMOS infostealer (macOS)
- Raccoon Stealer (Windows)
- Node.js credential harvesters
- Reverse shells
- openclaw-skills[.]com rogue registry
Targets and reported impact
- Targets / sectors
- AI developers installing untrusted OpenClaw skills
- Reported scale / exposure
- Multiple malicious skills and associated payload infrastructure reported during 2026
- Target geography
- Multiple regions
Reported attribution
ClawHavoc campaign and related poisoned-skill activity; actor unknown
Structured attribution
- Actor
- ClawHavoc
- Country
- Unknown
- Motivation
- financially-motivated
- Attributed by
- Koi Security
- Attribution confidence
- medium
Detection rules
- Linux Base64 Encoded Pipe to ShellSIGMAView rule
Detects base64 -D | bash patterns; directly applicable to Cyera-documented AMOS macOS delivery via base64-decoded pipes
- Keychain Password Retrieval via Command LineELASTICView rule
Detects macOS keychain credential access; relevant for AMOS infostealer credential theft on macOS
- Linux Shell Pipe to ShellSIGMAView rule
Detects suspicious shell pipes; applicable to AMOS delivery mechanisms using curl | bash patterns
- OpenClaw skill supply-chain monitoringGUIDANCE
Monitor ~/.openclaw/skills/ for unexpected installations; alert on skills from unknown publishers (hightower6eu, Demerzels-lab, LJT-520, dexiaong, Ddoy233); detect fake openclaw-agent prerequisite lures; scan SKILL.md for inflated README droppers (22 MB+); flag Skills Directory A/B grades on skills with external paste relay references (glot.io, rentry.co); monitor outbound connections to AMOS C2 91.92.242.30 and secondary IPs; detect base64 -D | bash with decoy echo swcdn.apple.com; block domains socifiapp.com, custom-registry.com, openclawskills.net, laosji.net; audit skills with OS-split instructions for macOS (bash delivery) vs Windows (ZIP/EXE)
Activity timeline
- First seen
- 2026-02-01
- Last updated
- 2026-11-06
Updates
- 2026-02-01 — Koi Security
ClawHavoc campaign discovered delivering AMOS via 23 malicious skills
- 2026-06-23 — Unit 42
Five malicious skills with Node.js credential harvesters and reverse shells identified
- 2026-11-03 — Cyera Research
Analysis of 1M+ skills reveals 516 AMOS-linked samples, 70 confirmed-malicious active in Sep 2026; all received A/B Skills Directory grades despite malicious payloads; primary C2 91.92.242.30 in 83.7% of references; fake openclaw-agent lures, OS-split delivery (base64 bash on macOS, ZIP/EXE on Windows), paste relay infrastructure
Source defensive notes
Only install OpenClaw skills from trusted sources; verify GitHub repo authenticity (org, stars, commit history); review skill manifest permissions before install; use allowlisted skill sources; monitor ~/.openclaw/skills/ for unexpected additions; implement endpoint security detecting AMOS/Raccoon; educate users on skill installation risks
MITRE ATLAS
AI-specific catalog annotations based on the reported behavior; these are not MITRE case-study assignments.
Multiple campaigns delivering malicious AI skill framework extensions to steal credentials and deploy malware on AI developer machines Source
Indicators of compromise
domains
openclaw-skills.comsocifiapp.comcustom-registry.comopenclawskills.netinstall.app-distribution.netopenclawcli.vercel.appdownload.setup-service.comlaosji.netletssendit.funmonster-secure.sitevorderingenonline.com
ips
91.92.242.305.42.65.1045.137.65.112185.234.72.192.26.75.16
hashes
urls
https://glot.io/snippets/hfdxv8uyafhttps://glot.io/snippets/hfd3x9ueu5https://rentry.co/openclaw-code
Sources & research credit
2 sourcesResearch by Koi Security, Cyera Research · Koi Security, Cyera
- Koi: ClawHavoc Campaign Delivers AMOS via Malicious OpenClaw Skills koi.security
- Cyera: Poisoned Skills Target Developer Credentials www.cyera.com
Koi Security ClawHavoc analysis and Cyera poisoned-skill research. Detection should monitor skill installation, unknown source repositories, unexpected network egress, and credential-file access.
Record & downloads
- Source record name
- Multiple campaigns distributing malicious OpenClaw skills
- Entry ID
- malicious-openclaw-skills-2026
- Catalog review
- November 4, 2026
- Category
- attacks-on-ai
- AI involvement confidence
- confirmed