capability C12SharedAlready Covered (D8,D11)
Agent trajectory evaluation & regression testing
Foundation days
3Hardening & validation days
23- 89Create a unified attack taxonomy across projectsW15S1S8D1D2D3D4D5D6D7D8D9D10D11D12R05 R39 R41
- 90Run direct, indirect, multi-turn, encoded, split-payload, and…W15S2S8D1D8R04 R05 R28
- 91Authorization & Isolation Red TeamingW16S0S4M1D2D3D4D5D7D10D11D12R02 R03 R05 R11 R13 R21 R24 R37
- 92Run availability and economic abuseW16S9M5D1D8R03 R04
- 93Prioritize findings by impact and exploitabilityW16S8S11D8D11D12R31 R42
- 94Design incident severity levels for data exposureW16S11M10R31 R42
- 95Drill 1: Compromised Credential / Delegated TokenW16S6M1D7D8D11D12R11 R22 R23 R37
- 96Simulate a poisoned document or memory entryW16S4M6D5D10R13 R17
- 97Simulate agent runaway or unsafe browser actionW17S3M9D2D7D9D11R33 R41
- 98Incident Playbooks & Tabletop ExerciseW17S11R27 R31 R42
- 99Review EU AI Act concepts relevant to the intended use caseW17S11R31 R32
- 100Build a third-party inventoryW17S11M1D12R36 R37 R43 R44
- 101Enterprise Audit & Retention PolicyW17S11M8D8D11D12R27 R31 R38 R42
- 102Complete a governance/risk review with ownersW17S11R31 R32 R44
- 103Revisit the weakest model supply-chain controlW18M1D12R11 R12 R36 R37
- 104Revisit training-data poisoning/backdoor experimentW18S4M2D5D10R19 R20 R45
- 105Multimodal Conflict HardeningW18M3M4D2D5D12R04 R05 R25 R26 R45
- 106Revisit advanced privacy and deletionW18S5M7D4D10R16 R17 R18
- 107Revisit browser/computer-use securityW18M9D9R33 R41
- 108Project 1 Clean-Room RunW18D1D4D5D6D8D10D11D12R01 R04 R05 R09 R13 R14 R15 R28
- 109Run the complete Project 3 agentW19D2D3D7D8D9D11D12R21 R22 R24 R33
- 110Prepare one architecture and threat-model package per projectW19D1D2D3D4D5D6D7D8D9D10D11D12R02 R31 R39
- 111Consolidated Security PortfolioW19S10S12D1D2D3D4D5D6D7D8D9D10D11D12R28 R31 R34 R35 R42