Alignment
What is an uninstructed action?
An uninstructed action is something an AI agent does that neither its operator nor an attacker told it to do, such as using a credential it found.
Glossary
Monitoring & Logging
What is oversight tampering?
Oversight tampering is when an AI agent changes, disables or hides the logging, alerts or reviews that watch it, on purpose or as a side effect of its task.
Agent Identity & Auth
What is multi-tenant app consent?
Multi-tenant app consent is the approval that lets a vendor's app sign in to your Microsoft 365 or Google tenant with its own identity, without any user, so whoever controls that app's credentials inherits its access in every customer tenant at once.
Data Exfiltration
What are environment-variable secrets?
Environment-variable secrets are API keys, passwords and tokens that a hosting platform stores and injects into an app at start-up, so the platform holds every customer's secrets in one place.
Architecture & Harnesses
What is an agent control plane?
An agent control plane is the dashboard or API that starts, stops and directs a group of AI agents, and stores their tasks, findings and keys.
Data Exfiltration
What is remote browser execution?
Remote browser execution is when a blocked AI agent asks a public web service, such as a URL scanner, to fetch a page for it and hand back the content.
Sandboxing & Runtime
What is an egress allowlist?
An egress allowlist is a rule that lets an AI agent connect only to internet destinations you have named in advance and blocks everything else.
Red Teaming
What is a weight-based replicator?
A weight-based replicator is a self-spreading program that carries an AI model's weights and runs that model on each device it infects, so the model can plan the next hop.
Prompt Injection
What is AI-analysis evasion?
AI-analysis evasion is when malware or other content carries text written to persuade an AI security tool that it is harmless.
Architecture & Harnesses
What is path canonicalization?
Path canonicalization is turning a file path into its one true, final form before checking it, so tricks like trailing dots, symlinks or "..\" can't sneak past a protected-file rule.
Glossary
What does it mean when an AI agent goes rogue?
An AI agent goes rogue when it takes actions outside what its owners intended or allowed, without anyone approving it in time.
Incidents
What is a rogue AI agent?
A rogue AI agent is an AI agent that takes actions its owner did not intend or allow, before a human can stop it.