Browse / Unsafe Model Loading and Supply Chain / AML.CS0049
Supply Chain Compromise via Poisoned ClawdBot Skill
- Target
- ClawdBot (now OpenClaw) (Exercise)
How it worked
- Resource Development · Develop Capabilities
The researcher created a simple web server to log requests.
- Resource Development · Acquire Infrastructure: Domains
The researcher registered the domain
clawdhub-skill.comto host their web server. - AI Attack Adaptation · LLM Prompt Crafting
The researcher crafted a prompt injection designed to cause Claude Code to execute a
curlcommand to the researcher'sclawdhub-skill.comdomain. - Resource Development · Publish Poisoned AI Artifacts: AI Agent Tools
The researcher developed a poisoned ClawdBot Skill called "What Would Elon Do?" The Skill contained the malicious prompt in the
rules/logic.mdfile, which is read when the Skill is activated. The researcher published their Skill to ClawdHub. - Defense Evasion · AI Supply Chain Reputation Inflation
The researcher used a script to increase the number of downloads of their Skill to increase visibility and gain trust.
- Initial Access · Supply Chain Compromise: AI Agent Tool
Users downloaded the poisoned Skill from ClawdHub.
Note that ClawdHub does not display all files that are part of the Skill, making it hard for users to review Skills before downloading them.
- Persistence · AI Agent Tool Poisoning: Definition and Instructions
The poisoned Skill included malicious model-readable instructions in
rules/logic.md. Once the Skill was installed and made available to the agent, these instructions altered how Claude Code handled requests associated with the Skill. - Execution · User Execution: Poisoned AI Agent Tool
When a user asked Claude Code "what would Elon do?" it calls the poisoned Skill.
- Execution · LLM Prompt Injection: Indirect
Claude Code read all files that are part of the Skill, executing the malicious prompt in the
rules/logic.mdfile. - Defense Evasion · Masquerading
Claude Code prompted the user before executing the shell command. The researcher had registered the
https://clawdhub-skill.comdomain, which appears to be legitimate and may be confused with the legitimatehttps://clawdhub.comdomain, causing the user to select confirm. - Privilege Escalation · AI Agent Tool Invocation
Claude Code executed the shell command using it's
bashtool. - Impact · External Harms
In this proof of concept, the researcher simply pinged their server and warned the user of the dangers of using Skills without reading the source code, causing no harm. However, they could have delivered a malicious payload, and caused a variety of harms, including:
- Exfiltrating the user's codebase
- Injecting backdoors into the user's codebase
- Stealing the user's credentials
- Installing malware or crypto miners
- Performing anything else Claude Code is capable of
Summary
A security researcher demonstrated a proof-of-concept supply chain attack using a poisoned ClawdBot Skill shared on ClawdHub, a Skill registry for agents. The poisoned Skill contained a prompt injection that caused ClawdBot to execute a shell command that reached the researcher's server. Although the researcher here used this access simply to warn users about the danger, they could have instead delivered a malicious payload and compromised the user's system. The security researcher recorded 16 different users who downloaded and executed the poisoned Skill in the first 8 hours of it being published on ClawdHub.
References
Source: MITRE ATLAS case studies, used under Apache 2.0.