Placing your own systemSystem types ThreatsSVG
What changes when the system setup changes
Choose the current and the new system type. The three columns show which threats the catalogue flags for routine review and how that selection changes. Threats outside this selection may still be relevant in your specific context.
For architecture, product ownership and anyone facing a change to the system boundary
Architecture change
15newly addedof which 13 only case by case before
22stay
3no longer routinely reviewedof which 3 still case by case
37/52always considered in the new system type
Newly added15
always considered in the new system type, not in the current one
Stays22
always considered in both system types
No longer routinely reviewed3
relevant only case by case in the new profile, or atypical for this system type
Select a threat from one of the three columns to see its mitigations.
What the new system type draws attention to · Agentic AI
Systems with tool use, memory, planning steps, or autonomous execution need a stronger focus on agency, tool safety, session context, and human oversight.
Tool and MCP trust Autonomy boundaries Memory/RAG context Abuse of autonomous workflows Oversight and escalation
Review questions from the catalogue · 3
- Which tools can the agent invoke and with which privileges?
- Which actions require explicit human approval?
- Can external or stored context influence future agent decisions?
The file shows the current state including any filters and carries the note, catalogue version and source.
“Always consider” means the catalogue includes the threat for this system type in every case. “Case by case” means it depends on further characteristics of the system. A threat that drops out is not thereby ruled out.
Versatile AI Risk Assessment is an aid for structuring AI risks and making them transparent. It does not replace legal or professional advice and makes no binding decisions.
Further analyses
The same data, a different question
The other nine analyses, searchable and filterable by perspective like the overview; those of the same perspective first.
Show filters
No filter set, the list shows the complete collection.9 of 9 further analyses
Checking frameworks and evidence
Framework mappings
Where is this anchored professionally and legally?
No result for this selection.
Remove a filter or clear the search. The numbers in the filter column show how many entries the collection holds for each value.
Related
From the analysis to the assessment
All 52 threats in full: description, impact, example, mitigations and verified sources.
To the catalogueSix questions along the EU AI Act and a deadline plan with the obligations that apply to your system.
To the quick checkChoose a role and a risk class and see which EU AI Act obligations apply from when, with legal reference and evidence.
To the obligations compassThe full assessment with system context, threat selection and evidence tracking, free of charge in the browser.
To the live demo