Threats
Prompt injection, memory poisoning, malicious skills, impostor apps and incidents.

My AI Agent Did Something I Didn't Ask For: What Happened and What to Do
If your AI agent sent, bought, shared or claimed something you never asked for, here is how to stop it, find out why, undo the damage and prevent a repeat.
Read My AI Agent Did Something I Didn't Ask For: What Happened and What to Do
AI Agent Memory Poisoning: How MemGhost-Style Attacks Plant False Memories
AI agent memory poisoning plants false facts in an agent's long-term memory, often via one email. How MemGhost worked, what you can check, and how to clean up.
Read AI Agent Memory Poisoning: How MemGhost-Style Attacks Plant False Memories
Fake AI Agent Apps, Extensions and Invites: How to Spot an Impostor
How to spot a fake AI agent app, extension or invite: where Muse, dots, Claude Duet, Grok Bot and OpenClaw really come from, and what to do if you got one.
Read Fake AI Agent Apps, Extensions and Invites: How to Spot an Impostor
Fake Agent Sign-In Pages: Why Real Agents Never Ask You to Log In by Link
Fake AI agent login pages steal passwords by link. How Claude Duet, Muse, Grok Bot and dots really handle sign-in, the red flags, and what to do if caught.
Read Fake Agent Sign-In Pages: Why Real Agents Never Ask You to Log In by Link
Indirect Prompt Injection: Real Examples in Email, Calendar Invites, Docs and Web Pages
Real indirect prompt injection examples for personal AI agents: hidden instructions in email, calendar invites, docs, web pages and messages, and how to defend.
Read Indirect Prompt Injection: Real Examples in Email, Calendar Invites, Docs and Web Pages
Is Self-Hosting an AI Agent Safe? The Honest Trade-Offs vs Hosted Agents
Is self-hosting an AI agent like OpenClaw safe? The real trade-offs against hosted agents like Muse and Claude Duet: control versus exposure and upkeep.
Read Is Self-Hosting an AI Agent Safe? The Honest Trade-Offs vs Hosted Agents
The Lethal Trifecta: Why Private Data, Untrusted Content and Outbound Access Don't Mix
The lethal trifecta: private data, untrusted content and a way to send data out. Why that mix makes AI agents leak, and how to break it for your own agent.
Read The Lethal Trifecta: Why Private Data, Untrusted Content and Outbound Access Don't Mix
Malicious Agent Skills: What ClawHavoc Taught Us About Skill Marketplaces
ClawHavoc planted hundreds of malicious OpenClaw skills on ClawHub in early 2026. What happened, how fake skills work, and how to vet skills before installing.
Read Malicious Agent Skills: What ClawHavoc Taught Us About Skill Marketplaces
MCP Server Security Risks for Personal Agents: Tool Poisoning and Over-Broad Connectors
MCP server security risks for personal agents: tool poisoning, rug pulls, tool shadowing, malicious local servers and over-broad scopes, and how to limit them.
Read MCP Server Security Risks for Personal Agents: Tool Poisoning and Over-Broad Connectors
The Meta Muse Zero-Day, Explained: What the Hidden-Setting Flaw Exposed
In September 2026 Patrick Wardle disclosed a Meta Muse Mac flaw that let local malware redirect dictation. What it exposed, what was fixed and what to do.
Read The Meta Muse Zero-Day, Explained: What the Hidden-Setting Flaw Exposed