Loading content
Agent Scan inventories agent ecosystem components and looks for prompt injection, tool poisoning, secrets, and unsafe permissions. Findings need validation in the local environment.
Use this profile to understand the building block briefly, place it in the model, and open related building blocks.
Usable application software: supports people in a task.
Concrete cog in the system that works inside larger relationships.
Agent Scan is a checking tool that examines agent or AI systems for detectable risks, configuration errors, and security weaknesses.
Agent Scan was classified as a tool in the Thoughtworks Technology Radar context. It reflects the newer practice of systematically examining AI agents with specialized scanners and security checks before production use.
A scanner reads configurations, dependencies, and reachable interfaces, compares them with known rules, and reports findings. A finding is a prompt for investigation; the team still assesses and remediates it.
An automated check that evaluates technical artifacts against rules.
A recorded indication of a possible risk or misconfiguration.
Ranking a finding by relevance, exploitability, and urgency.
Agent Scan can bring early security checks into development and operations; a scanner sees only patterns it can encode and does not replace threat modeling or manual review.
Where this building block is located in the topic model.
No structure path available.
Explore how this building block connects to concepts, methods, technologies, and tools.
These sources establish the term and its professional meaning.
All direct connections of the current building block in a compact text view.
This classification shows where the building block typically matters, how demanding it is, and what kind of impact it has in the model.
The level within the organization (enterprise, domain, team) at which the AssetBlock is applied.