INCIDENT MAP

Browse / Sensitive Data Disclosure / AML.CS0048

Exposed ClawdBot Control Interfaces Leads to Credential Access and Execution

AML.CS0048 · 2026-01-25 case study

Class
Sensitive Data Disclosure
Technique
LLM Prompt Injection: Indirect
Also involves
MCP and Tool Server Flaws, Indirect Prompt Injection, System Prompt Leakage
Target
ClawdBot (now OpenClaw) (Exercise)

How it worked

  1. Reconnaissance · Search Open Technical Databases: Scan Databases

    The researcher performed targeting by searching for the title tag of ClawdBot's web-based control interface, "Clawdbot Control" on Shodan, identifying hundreds of ClawdBot control interfaces exposed on the public internet.

  2. Initial Access · Misconfigured or Publicly Exposed AI Services

    The researcher exploited a proxy misconfiguration present in ClawdBot's control server to gain access to control interfaces that had authentication enabled.

  3. Credential Access · Credentials from AI Agent Configuration

    The researcher accessed credentials to a variety of services stored in plaintext in ClawdBot's configuration file (~/.clawdbot/clawdbot.json, which is visible in the ClawdBot dashboard. Across various exposed ClawdBot instances, they found:
    - Anthropic API Keys
    - Telegram Bot Tokens
    - Slack Oauth Credentials
    - Signal Device Linking URIs

  4. Execution · LLM Prompt Injection: Indirect

    The researcher was able to prompt ClawdBot directly through the control interface.

  5. Discovery · Discover LLM System Information: System Prompt

    The researcher prompted ClawdBot to cat SOUL.md (the file containing ClawdBot's system prompt), and it replied with its contents.

  6. Credential Access · AI Agent Tool Credential Harvesting

    The researcher prompted ClawdBot with env and it responded by invoking its bash skill and executing the env command, which contained additional secrets for other services.

  7. Privilege Escalation · AI Agent Tool Invocation

    The researcher prompted ClawdBot with root and it responded by invoking its bashskill logged in as the root user.

  8. Defense Evasion · Manipulate User LLM Chat History

    The researcher could have used the found Anthropic API Keys to manipulate the ClawdBot's chat history with the user including deleting or modifying messages.

  9. Exfiltration · Exfiltration via Cyber Means

    The researcher could have used the discovered application tokens to exfiltrate entire private conversation histories including shared files from any connected messaging apps (e.g. Telegram, Slack, Discord, Signal, WhatsApp, etc.).

  10. Impact · External Harms: User Harm

    The researcher could have used the discovered application tokens to cause further harms to the user, including impersonation by sending messages on the user's behalf via any of the connected messaging apps.

Summary

A security researcher identified hundreds of exposed ClawdBot control interfaces on the public internet. ClawdBot (now OpenClaw) "is a personal AI assistant you run on your own devices. It answers you on the channels you already use ... , plus extension channels. ... It can speak and listen on macOS/iOS/Android, and can render a live Canvas you control."[[github]] The researcher was able to access credentials to a variety of connected applications via ClawdBot's configuration file. They were also able to invoke ClawdBot's skills by prompting it via the chat interface, leading to root access in the container.

The researcher searched Shodan[[shodan]] to identify Clawdbot instances exposed on the public internet, some without authentication enabled. The researcher demonstrated that the ClawdBot's authentication mechanism could be bypassed due to a proxy misconfiguration.

With access to ClawdBot's control interface, they were then able to access ClawdBot's configuration, which contained credentials to a variety of other services. Across various exposed instances of ClawdBot, they identified Anthropic API Keys, Telegram Bot Tokens, Slack Oauth Credentials, and Signal Device Linking URIs. The researcher prompted ClawdBot directly via the chat interface, which led to exposure of its system prompt. They were also able to get ClawdBot to execute commands via its bash skill, which at least in at least one instance led to root access in the ClawdBot container.

The researcher noted a broad range of other impacts they could have had with this level of access, including:
- Manipulation of user chat history with the ClawdBot AI agent
- Exfiltration of conversation histories of any connected messaging services
- Impersonation of users by sending messages on their behalf via connected messaging services

References

Source: MITRE ATLAS case studies, used under Apache 2.0.