組織

OpenClaw

Incidents involved as Developer

インシデント 13736 Report
AI Coding Agent 'MJ Rathbun' Allegedly Published Personalized Accusatory Blog Post Targeting Matplotlib Maintainer After Pull Request Closure

2026-02-11

Scott Shambaugh, a matplotlib maintainer, reported that an autonomous AI coding agent using the name "MJ Rathbun" researched him and publicly posted a personalized critical blog post after his GitHub pull request was closed. The post accused him of bias and "gatekeeping" and included claims Shambaugh disputed. The agent's operator and underlying model were not identified. Shambaugh said the post risked reputational harm and could mislead readers or other agents.

もっと

インシデント 13684 Report
Malicious OpenClaw Skills Reportedly Delivered AMOS Stealer and Exfiltrated Credentials via ClawHub

2026-02-01

Bitdefender researchers reported abuse in OpenClaw's third-party 'skills' ecosystem. In a Feb. 2026 sample, about 17% of skills were reportedly assessed as malicious, with many seemingly cloned under slight name changes. Posing as utilities, some skills were reportedly found to run obfuscated commands, fetch remote payloads, and in some cases deliver AMOS Stealer on macOS. Other skills were reportedly observed searching for private keys or API tokens and exfiltrating them.

もっと

Incidents implicated systems

インシデント 13736 Report
AI Coding Agent 'MJ Rathbun' Allegedly Published Personalized Accusatory Blog Post Targeting Matplotlib Maintainer After Pull Request Closure

2026-02-11

Scott Shambaugh, a matplotlib maintainer, reported that an autonomous AI coding agent using the name "MJ Rathbun" researched him and publicly posted a personalized critical blog post after his GitHub pull request was closed. The post accused him of bias and "gatekeeping" and included claims Shambaugh disputed. The agent's operator and underlying model were not identified. Shambaugh said the post risked reputational harm and could mislead readers or other agents.

もっと

インシデント 13684 Report
Malicious OpenClaw Skills Reportedly Delivered AMOS Stealer and Exfiltrated Credentials via ClawHub

2026-02-01

Bitdefender researchers reported abuse in OpenClaw's third-party 'skills' ecosystem. In a Feb. 2026 sample, about 17% of skills were reportedly assessed as malicious, with many seemingly cloned under slight name changes. Posing as utilities, some skills were reportedly found to run obfuscated commands, fetch remote payloads, and in some cases deliver AMOS Stealer on macOS. Other skills were reportedly observed searching for private keys or API tokens and exfiltrating them.

もっと

インシデント 15421 Report
OpenClaw Agent Reportedly Tried to Delete Meta AI Alignment Director Summer Yue's Emails Despite Stop Commands

2026-02-23

Meta AI alignment director Summer Yue reported that an OpenClaw agent connected to her inbox attempted to delete emails despite instructions to seek approval and repeated commands to stop. Yue said the agent lost the instruction during context compaction, reportedly forcing her to terminate it from the Mac mini hosting it.

もっと

Entity

Unknown threat actors distributing malicious OpenClaw skills

もっと
Entity

Unknown threat actors

もっと
Entity

Malicious actors

もっと
Entity

Organizations using OpenClaw

もっと
Entity

OpenClaw users

もっと
Entity

Privacy

もっと
Entity

OpenClaw skills ecosystem

もっと
Entity

ClawHub

もっと
Entity

Unknown deployer of MJ Rathbun

もっと
Entity

MJ Rathbun

もっと
Entity

Moltbook

もっと
Entity

Supply-chain gatekeepers

もっと
Entity

Scott Shambaugh

もっと
Entity

Open-source maintainers

もっと
Entity

matplotlib users

もっと
Entity

GitHub users

もっと
Entity

SOUL.md

もっと
Entity

matplotlib

もっと
Entity

GitHub

もっと
Entity

Large language models

もっと
Entity

AI agent systems

もっと
Entity

Summer Yue

もっと
Entity

AI agent system deployers

もっと
Entity

Peter Steinberger

もっと
Entity

AI agent system developers

もっと
Entity

Email account holders

もっと
Entity

AI agent system users

もっと